pretty good

app.py

@@ -2,10 +2,9 @@ import matplotlib.pyplot as plt
 import matplotlib
 import pandas as pd
 import gradio as gr
+import random
 
-from data import CIResults
 from utils import logger
-from summary_page import create_summary_page
 
 
 # Configure matplotlib to prevent memory warnings and set dark background
@@ -15,27 +14,26 @@ matplotlib.rcParams['savefig.facecolor'] = '#000000'
 plt.ioff()  # Turn off interactive mode to prevent figure accumulation
 
 
-# Load data once at startup
-Ci_results = CIResults()
-Ci_results.load_data()
-# Start the auto-reload scheduler
-Ci_results.schedule_data_reload()
+# Function to generate random data for the plot
+def generate_random_data():
+    """Generate random data points for the scatter plot."""
+    n_points = random.randint(20, 50)  # Random number of points
+    x_data = [random.uniform(-100, 100) for _ in range(n_points)]
+    y_data = [random.uniform(-100, 100) for _ in range(n_points)]
+    return pd.DataFrame({"x": x_data, "y": y_data})
 
 
 # Function to get current description text
 def get_description_text():
-    """Get description text with integrated last update time."""
+    """Get description text."""
     msg = [
-        "Transformer CI Dashboard",
+        "Random Data Dashboard",
         "-",
-        "AMD runs on MI325",
-        "NVIDIA runs on A10",
+        "Click summary to refresh data",
+        "Demo visualization",
     ]
     msg = ["**" + x + "**" for x in msg] + [""]
-    if Ci_results.latest_update_msg:
-        msg.append(f"*This dashboard only tracks important models*<br>*({Ci_results.latest_update_msg})*")
-    else:
-        msg.append("*This dashboard only tracks important models*<br>*(loading...)*")
+    msg.append("*Random scatter plot data*<br>*Updated on each click*")
     return "<br>".join(msg)
 
 # Load CSS from external file
@@ -71,17 +69,12 @@ with gr.Blocks(title="Model Test Results Dashboard", css=load_css(), fill_height
                 elem_classes=["summary-button"]
             )
 
-            # CI job links at bottom of sidebar
-            ci_links_display = gr.Markdown("🔗 **CI Jobs:** *Loading...*", elem_classes=["sidebar-links"])
 
         # Main content area
         with gr.Column(elem_classes=["main-content"]):
             # Summary display (default view)
             summary_display = gr.ScatterPlot(
-                pd.DataFrame({
-                    "x": [i for i in range(10)] + [100, -100],
-                    "y": [i ** 2 for i in range(10)] + [100, -100],
-                }),
+                generate_random_data(),
                 x = "x",
                 y = "y",
                 height="100vh",
@@ -93,89 +86,20 @@ with gr.Blocks(title="Model Test Results Dashboard", css=load_css(), fill_height
 
 
     # Summary button click handler
-    def show_summary_and_update_links():
-        """Show summary page and update CI links."""
-        return create_summary_page(Ci_results.df, Ci_results.available_models), get_description_text(), get_ci_links()
+    def refresh_plot_data():
+        """Generate new random data for the plot."""
+        new_data = generate_random_data()
+        return new_data, get_description_text()
 
     summary_button.click(
-        fn=show_summary_and_update_links,
-        outputs=[summary_display, description_display, ci_links_display]
+        fn=refresh_plot_data,
+        outputs=[summary_display, description_display]
     )
 
-    # Function to get CI job links
-    def get_ci_links():
-        """Get CI job links from the most recent data."""
-        try:
-            # Check if df exists and is not empty
-            if Ci_results.df is None or Ci_results.df.empty:
-                return "🔗 **CI Jobs:** *Loading...*"
-
-            # Get links from any available model (they should be the same for all models in a run)
-            amd_multi_link = None
-            amd_single_link = None
-            nvidia_multi_link = None
-            nvidia_single_link = None
-
-            for model_name in Ci_results.df.index:
-                row = Ci_results.df.loc[model_name]
-
-                # Extract AMD links
-                if pd.notna(row.get('job_link_amd')) and (not amd_multi_link or not amd_single_link):
-                    amd_link_raw = row.get('job_link_amd')
-                    if isinstance(amd_link_raw, dict):
-                        if 'multi' in amd_link_raw and not amd_multi_link:
-                            amd_multi_link = amd_link_raw['multi']
-                        if 'single' in amd_link_raw and not amd_single_link:
-                            amd_single_link = amd_link_raw['single']
-
-                # Extract NVIDIA links
-                if pd.notna(row.get('job_link_nvidia')) and (not nvidia_multi_link or not nvidia_single_link):
-                    nvidia_link_raw = row.get('job_link_nvidia')
-                    if isinstance(nvidia_link_raw, dict):
-                        if 'multi' in nvidia_link_raw and not nvidia_multi_link:
-                            nvidia_multi_link = nvidia_link_raw['multi']
-                        if 'single' in nvidia_link_raw and not nvidia_single_link:
-                            nvidia_single_link = nvidia_link_raw['single']
-
-                # Break if we have all links
-                if amd_multi_link and amd_single_link and nvidia_multi_link and nvidia_single_link:
-                    break
-
-
-            # Add FAQ link at the bottom
-            links_md = "❓ [**FAQ**](https://huggingface.co/spaces/transformers-community/transformers-ci-dashboard/blob/main/README.md)\n\n"
-            links_md += "🔗 **CI Jobs:**\n\n"
-
-            # AMD links
-            if amd_multi_link or amd_single_link:
-                links_md += "**AMD:**\n"
-                if amd_multi_link:
-                    links_md += f"• [Multi GPU]({amd_multi_link})\n"
-                if amd_single_link:
-                    links_md += f"• [Single GPU]({amd_single_link})\n"
-                links_md += "\n"
-
-            # NVIDIA links
-            if nvidia_multi_link or nvidia_single_link:
-                links_md += "**NVIDIA:**\n"
-                if nvidia_multi_link:
-                    links_md += f"• [Multi GPU]({nvidia_multi_link})\n"
-                if nvidia_single_link:
-                    links_md += f"• [Single GPU]({nvidia_single_link})\n"
-
-            if not (amd_multi_link or amd_single_link or nvidia_multi_link or nvidia_single_link):
-                links_md += "*No links available*"
-
-            return links_md
-        except Exception as e:
-            logger.error(f"getting CI links: {e}")
-            return "🔗 **CI Jobs:** *Error loading links*\n\n❓ **[FAQ](README.md)**"
-
-
-    # Auto-update CI links when the interface loads
+    # Auto-update description when the interface loads
     demo.load(
-        fn=get_ci_links,
-        outputs=[ci_links_display]
+        fn=get_description_text,
+        outputs=[description_display]
     )
 
 

data.py

@@ -1,227 +0,0 @@
-from huggingface_hub import HfFileSystem
-import pandas as pd
-from utils import logger
-import threading
-import traceback
-import json
-import re
-
-# NOTE: if caching is an issue, try adding `use_listings_cache=False`
-fs = HfFileSystem()
-
-IMPORTANT_MODELS = [
-    "auto",
-    "bert",  # old but dominant (encoder only)
-    "gpt2",  # old (decoder)
-    "t5",  # old (encoder-decoder)
-    "modernbert",  # (encoder only)
-    "vit",  # old (vision) - fixed comma
-    "clip",  # old but dominant (vision)
-    "detr",  # objection detection, segmentation (vision)
-    "table_transformer",  # objection detection (visioin) - maybe just detr?
-    "got_ocr2",  # ocr (vision)
-    "whisper",  # old but dominant (audio)
-    "wav2vec2",  # old (audio)
-    "qwen2_audio",  # (audio)
-    "speech_t5",  # (audio)
-    "csm",  # (audio)
-    "llama",  # new and dominant (meta)
-    "gemma3",  # new (google)
-    "qwen2",  # new (Alibaba)
-    "mistral3",  # new (Mistral) - added missing comma
-    "qwen2_5_vl",  # new (vision)
-    "llava",  # many models from it (vision)
-    "smolvlm",  # new (video)
-    "internvl",  # new (video)
-    "gemma3n",  # new (omnimodal models)
-    "qwen2_5_omni",  # new (omnimodal models)
-    # "gpt_oss",  # new (quite used)
-    "qwen2_5_omni",  # new (omnimodal models)
-]
-
-KEYS_TO_KEEP = [
-    "success_amd",
-    "success_nvidia",
-    "skipped_amd",
-    "skipped_nvidia",
-    "failed_multi_no_amd",
-    "failed_multi_no_nvidia",
-    "failed_single_no_amd",
-    "failed_single_no_nvidia",
-    "failures_amd",
-    "failures_nvidia",
-    "job_link_amd",
-    "job_link_nvidia",
-]
-
-
-def log_dataframe_link(link: str) -> str:
-    """
-    Adds the link to the dataset in the logs, modifies it to get a clockable link and then returns the date of the 
-    report.
-    """
-    logger.info(f"Reading df located at {link}")
-    # Make sure the links starts with an http adress
-    if link.startswith("hf://"):
-        link = "https://huggingface.co/" + link.removeprefix("hf://")
-    # Pattern to match transformers_daily_ci followed by any path, then a date (YYYY-MM-DD format)
-    pattern = r'transformers_daily_ci(.*?)/(\d{4}-\d{2}-\d{2})'
-    match = re.search(pattern, link)
-    # Failure case: 
-    if not match:
-        logger.error("Could not find transformers_daily_ci and.or date in the link")
-        return "9999-99-99"
-    # Replace the path between with blob/main
-    path_between = match.group(1)
-    link = link.replace("transformers_daily_ci" + path_between, "transformers_daily_ci/blob/main")
-    logger.info(f"Link to data source: {link}")
-    # Return the date
-    return match.group(2)
-
-def infer_latest_update_msg(date_df_amd: str, date_df_nvidia: str) -> str:
-    # Early return if one of the dates is invalid
-    if date_df_amd.startswith("9999") and date_df_nvidia.startswith("9999"):
-        return "could not find last update time"
-    # Warn if dates are not the same
-    if date_df_amd != date_df_nvidia:
-        logger.warning(f"Different dates found: {date_df_amd} (AMD) vs {date_df_nvidia} (NVIDIA)")
-    # Take the latest date and format it
-    try:
-        latest_date = max(date_df_amd, date_df_nvidia)
-        yyyy, mm, dd = latest_date.split("-")
-        return f"last updated {mm}/{dd}/{yyyy}"
-    except Exception as e:
-        logger.error(f"When trying to infer latest date, got error {e}")
-        return "could not find last update time"
-
-def read_one_dataframe(json_path: str, device_label: str) -> tuple[pd.DataFrame, str]:
-    df_upload_date = log_dataframe_link(json_path)
-    df = pd.read_json(json_path, orient="index")
-    df.index.name = "model_name"
-    df[f"failed_multi_no_{device_label}"] = df["failures"].apply(lambda x: len(x["multi"]) if "multi" in x else 0)
-    df[f"failed_single_no_{device_label}"] = df["failures"].apply(lambda x: len(x["single"]) if "single" in x else 0)
-    return df, df_upload_date
-
-def get_first_working_df(file_list: list[str]) -> str:
-    for file in file_list:
-        job_links = file.rsplit('/', 1)[0] + "/job_links.json"
-        try:
-            links = pd.read_json(f"hf://{job_links}", typ="series")
-            has_one_working_link = any(links.values)
-        except Exception as e:
-            logger.error(f"Could not read job links from {job_links}: {e}")
-            has_one_working_link = False
-        if has_one_working_link:
-            return file
-        logger.warning(f"Skipping {file} as it has no working job links.")
-    raise RuntimeError("Could not find any working dataframe in the provided list.")
-
-
-def get_sample_data() -> tuple[pd.DataFrame, str]:
-    # Retrieve sample dataframes
-    df_amd, _ = read_one_dataframe("sample_amd.json", "amd")
-    df_nvidia, _ = read_one_dataframe("sample_nvidia.json", "nvidia")
-    # Join both dataframes
-    joined = df_amd.join(df_nvidia, rsuffix="_nvidia", lsuffix="_amd", how="outer")
-    joined = joined[KEYS_TO_KEEP]
-    joined.index = joined.index.str.replace("^models_", "", regex=True)
-    # Fitler out all but important models
-    important_models_lower = [model.lower() for model in IMPORTANT_MODELS]
-    filtered_joined = joined[joined.index.str.lower().isin(important_models_lower)]
-    # Prefix all model names with "sample_"
-    filtered_joined.index = "sample_" + filtered_joined.index
-    return filtered_joined, "sample data was loaded"
-
-def safe_extract(row: pd.DataFrame, key: str) -> int:
-    return int(row.get(key, 0)) if pd.notna(row.get(key, 0)) else 0
-
-def extract_model_data(row: pd.Series) -> tuple[dict[str, int], dict[str, int], int, int, int, int]:
-    """Extract and process model data from DataFrame row."""
-    # Handle missing values and get counts directly from dataframe
-    success_nvidia = safe_extract(row, "success_nvidia")
-    success_amd = safe_extract(row, "success_amd")
-
-    skipped_nvidia = safe_extract(row, "skipped_nvidia")
-    skipped_amd = safe_extract(row, "skipped_amd")
-    
-    failed_multi_amd = safe_extract(row, 'failed_multi_no_amd')
-    failed_multi_nvidia = safe_extract(row, 'failed_multi_no_nvidia')
-    failed_single_amd = safe_extract(row, 'failed_single_no_amd')
-    failed_single_nvidia = safe_extract(row, 'failed_single_no_nvidia')
-    # Calculate total failures
-    total_failed_amd = failed_multi_amd + failed_single_amd
-    total_failed_nvidia = failed_multi_nvidia + failed_single_nvidia
-    # Create stats dictionaries directly from dataframe values
-    amd_stats = {
-        'passed': success_amd,
-        'failed': total_failed_amd,
-        'skipped': skipped_amd,
-        'error': 0     # Not available in this dataset
-    }
-    nvidia_stats = {
-        'passed': success_nvidia,
-        'failed': total_failed_nvidia,
-        'skipped': skipped_nvidia,
-        'error': 0     # Not available in this dataset
-    }
-    return amd_stats, nvidia_stats, failed_multi_amd, failed_single_amd, failed_multi_nvidia, failed_single_nvidia
-
-
-
-class CIResults:
-
-    def __init__(self):
-        self.df = pd.DataFrame()
-        self.available_models = []
-        self.latest_update_msg = ""
-
-    def load_data(self) -> None:
-        """Load data from the data source."""
-        # Try loading the distant data, and fall back on sample data for local tinkering
-
-        error_msg = [
-            "Loading data failed:",
-            "-" * 120,
-            traceback.format_exc(),
-            "-" * 120,
-            "Falling back on sample data."
-        ]
-        logger.error("\n".join(error_msg))
-        new_df, latest_update_msg = get_sample_data()
-        self.latest_update_msg = latest_update_msg
-
-        # Update attributes
-        self.df = new_df
-        self.available_models = new_df.index.tolist()
-        # Log and return distant load status
-        logger.info(f"Data loaded successfully: {len(self.available_models)} models")
-        logger.info(f"Models: {self.available_models[:5]}{'...' if len(self.available_models) > 5 else ''}")
-        logger.info(f"Latest update message: {self.latest_update_msg}")
-        # Log a preview of the df
-        msg = {}
-        for model in self.available_models[:3]:
-            msg[model] = {}
-            for col in self.df.columns:
-                value = self.df.loc[model, col]
-                if not isinstance(value, int):
-                    value = str(value)
-                    if len(value) > 10:
-                        value = value[:10] + "..."
-                msg[model][col] = value
-        logger.info(json.dumps(msg, indent=4))
-
-    def schedule_data_reload(self):
-        """Schedule the next data reload."""
-        def reload_data():
-            self.load_data()
-            # Schedule the next reload in 15 minutes (900 seconds)
-            timer = threading.Timer(900.0, reload_data)
-            timer.daemon = True  # Dies when main thread dies
-            timer.start()
-            logger.info("Next data reload scheduled in 15 minutes")
-
-        # Start the first reload timer
-        timer = threading.Timer(900.0, reload_data)
-        timer.daemon = True
-        timer.start()
-        logger.info("Data auto-reload scheduled every 15 minutes")

sample_amd.json

@@ -1,1839 +0,0 @@
-{
-    "models_auto": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 80,
-        "skipped": 2,
-        "time_spent": "0.99, 2.41, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329937",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330183"
-        }
-    },
-    "models_bert": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 239,
-        "skipped": 111,
-        "time_spent": "8.85, 0:01:00, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329946",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330199"
-        }
-    },
-    "models_clip": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 288,
-        "skipped": 590,
-        "time_spent": "0:01:55, 0:01:58, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330217",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329991"
-        }
-    },
-    "models_detr": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 77,
-        "skipped": 159,
-        "time_spent": "4.40, 6.77, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330035",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330267"
-        }
-    },
-    "models_gemma3": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 6,
-                "multi": 7
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 349,
-        "skipped": 260,
-        "time_spent": "0:11:14, 0:11:08, ",
-        "failures": {
-            "single": [
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_1b_text_only",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['Wri[57 chars]s, a silent stream,\\nInto the neural net, a wa[42 chars],\\n'] != ['Wri[57 chars]s, a river deep,\\nWith patterns hidden, secret[46 chars]ing']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [264 chars]cow\"] != ['use[114 chars]rown and white cow standing on a sandy beach n[272 chars]ach']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"user\\nYou are a helpful assistant.\\n\\nHe[678 chars]h a'] != ['user\\nYou are a helpful assistant.\\n\\nHe[658 chars]h a']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_bf16",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [55 chars]ike'] != ['use[114 chars]rown and white cow standing on a sandy beach w[68 chars]oks']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_crops",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[251 chars]. There's a blue sky with some white clouds in the background\"] != [\"use[251 chars]. There's a bright blue sky with some white clouds in the\"]"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_multiimage",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[122 chars]n\\n**Main Features:**\\n\\n*   **Chinese Archway[19 chars]ent\"] != [\"use[122 chars]n\\n**Overall Scene:**\\n\\nIt looks like a stree[18 chars]nt,\"]"
-                }
-            ],
-            "multi": [
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_model_parallelism",
-                    "trace": "(line 925)  RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_1b_text_only",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['Wri[57 chars]s, a silent stream,\\nInto the neural net, a wa[42 chars],\\n'] != ['Wri[57 chars]s, a river deep,\\nWith patterns hidden, secret[46 chars]ing']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [264 chars]cow\"] != ['use[114 chars]rown and white cow standing on a sandy beach n[272 chars]ach']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_batch_crops",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"user\\nYou are a helpful assistant.\\n\\nHe[678 chars]h a'] != ['user\\nYou are a helpful assistant.\\n\\nHe[658 chars]h a']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_bf16",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['use[114 chars]rown cow standing on a sandy beach with clear [55 chars]ike'] != ['use[114 chars]rown and white cow standing on a sandy beach w[68 chars]oks']"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_crops",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[251 chars]. There's a blue sky with some white clouds in the background\"] != [\"use[251 chars]. There's a bright blue sky with some white clouds in the\"]"
-                },
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3IntegrationTest::test_model_4b_multiimage",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"use[122 chars]n\\n**Main Features:**\\n\\n*   **Chinese Archway[19 chars]ent\"] != [\"use[122 chars]n\\n**Overall Scene:**\\n\\nIt looks like a stree[18 chars]nt,\"]"
-                }
-            ]
-        },
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330061",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330319"
-        }
-    },
-    "models_gemma3n": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 197,
-        "skipped": 635,
-        "time_spent": "0:01:06, 0:01:08, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330294",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330077"
-        }
-    },
-    "models_got_ocr2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 147,
-        "skipped": 163,
-        "time_spent": "0:01:03, 0:01:01, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330314",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330094"
-        }
-    },
-    "models_gpt2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 249,
-        "skipped": 99,
-        "time_spent": "0:02:01, 0:01:46, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330311",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330113"
-        }
-    },
-    "models_internvl": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 253,
-        "skipped": 107,
-        "time_spent": "0:01:50, 0:02:00, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_forward",
-                    "trace": "(line 727)  AssertionError: False is not true : Actual logits: tensor([ -9.8750,  -0.4885,   1.4668, -10.3359, -10.3359], dtype=torch.float16)"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLLlamaIntegrationTest::test_llama_small_model_integration_forward",
-                    "trace": "(line 727)  AssertionError: False is not true : Actual logits: tensor([ -9.8750,  -0.4885,   1.4668, -10.3359, -10.3359], dtype=torch.float16)"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330361",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330105"
-        }
-    },
-    "models_llama": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 235,
-        "skipped": 101,
-        "time_spent": "0:03:15, 0:02:51, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16",
-                    "trace": "(line 727)  AssertionError: False is not true"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/llama/test_modeling_llama.py::LlamaIntegrationTest::test_model_7b_logits_bf16",
-                    "trace": "(line 727)  AssertionError: False is not true"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330531",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330138"
-        }
-    },
-    "models_llava": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 206,
-        "skipped": 124,
-        "time_spent": "0:03:58, 0:04:34, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation",
-                    "trace": "(line 399)  importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/llava/test_modeling_llava.py::LlavaForConditionalGenerationIntegrationTest::test_batched_generation",
-                    "trace": "(line 399)  importlib.metadata.PackageNotFoundError: No package metadata was found for bitsandbytes"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330406",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330161"
-        }
-    },
-    "models_mistral3": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 199,
-        "skipped": 105,
-        "time_spent": "0:04:34, 0:04:39, ",
-        "failures": {
-            "single": [
-                {
-                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3IntegrationTest::test_mistral3_integration_generate",
-                    "trace": "(line 715)  AssertionError: 'The [14 chars] two cats lying on a pink surface, which appea[21 chars] bed' != 'The [14 chars] two tabby cats lying on a pink surface, which[23 chars]n or'"
-                }
-            ],
-            "multi": [
-                {
-                    "line": "tests/models/mistral3/test_modeling_mistral3.py::Mistral3IntegrationTest::test_mistral3_integration_generate",
-                    "trace": "(line 715)  AssertionError: 'The [14 chars] two cats lying on a pink surface, which appea[21 chars] bed' != 'The [14 chars] two tabby cats lying on a pink surface, which[23 chars]n or'"
-                }
-            ]
-        },
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330418",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329678"
-        }
-    },
-    "models_modernbert": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 142,
-        "skipped": 102,
-        "time_spent": "0:01:03, 9.02, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329712",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330429"
-        }
-    },
-    "models_qwen2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 217,
-        "skipped": 113,
-        "time_spent": "0:01:08, 0:01:05, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['My [35 chars], organic, gluten free, vegan, and vegetarian. I love to use'] != ['My [35 chars], organic, gluten free, vegan, and free from preservatives. I']"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/qwen2/test_modeling_qwen2.py::Qwen2IntegrationTest::test_export_static_cache",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['My [35 chars], organic, gluten free, vegan, and vegetarian. I love to use'] != ['My [35 chars], organic, gluten free, vegan, and free from preservatives. I']"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329761",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330508"
-        }
-    },
-    "models_qwen2_5_omni": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 2,
-                "multi": 2
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 167,
-        "skipped": 141,
-        "time_spent": "0:02:23, 0:01:53, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_model_parallelism",
-                    "trace": "(line 715)  AssertionError: Items in the second set but not the first:"
-                },
-                {
-                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"sys[293 chars]s shattering, and the dog appears to be a Labrador Retriever.\"] != [\"sys[293 chars]s shattering, and the dog is a Labrador Retriever.\"]"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test",
-                    "trace": "(line 700)  requests.exceptions.ConnectionError: HTTPSConnectionPool(host='qianwen-res.oss-accelerate-overseas.aliyuncs.com', port=443): Max retries exceeded with url: /Qwen2-VL/demo_small.jpg (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7cb8c91d02f0>: Failed to establish a new connection: [Errno -2] Name or service not known'))"
-                },
-                {
-                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniModelIntegrationTest::test_small_model_integration_test_batch",
-                    "trace": "(line 715)  AssertionError: Lists differ: [\"sys[109 chars]d is a glass shattering, and the dog is a Labr[187 chars]er.\"] != [\"sys[109 chars]d is glass shattering, and the dog is a Labrad[185 chars]er.\"]"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329806",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330503"
-        }
-    },
-    "models_qwen2_5_vl": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 205,
-        "skipped": 113,
-        "time_spent": "0:02:32, 0:02:29, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
-                    "trace": "(line 715)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329760",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330498"
-        }
-    },
-    "models_smolvlm": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 323,
-        "skipped": 231,
-        "time_spent": "0:01:08, 0:01:13, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330553",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329835"
-        }
-    },
-    "models_t5": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 2,
-                "multi": 3
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 254,
-        "skipped": 325,
-        "time_spent": "0:01:50, 0:01:40, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_multi_gpu_data_parallel_forward",
-                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
-                },
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
-                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
-                },
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_small_integration_test",
-                    "trace": "(line 727)  AssertionError: False is not true"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
-                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
-                },
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_small_integration_test",
-                    "trace": "(line 727)  AssertionError: False is not true"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329815",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330559"
-        }
-    },
-    "models_vit": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 135,
-        "skipped": 93,
-        "time_spent": "9.85, 7.74, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329875",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330596"
-        }
-    },
-    "models_wav2vec2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 292,
-        "skipped": 246,
-        "time_spent": "0:01:56, 0:01:54, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329877",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330632"
-        }
-    },
-    "models_whisper": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 40,
-                "multi": 42
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 537,
-        "skipped": 337,
-        "time_spent": "0:03:23, 0:03:02, ",
-        "failures": {
-            "single": [
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_distil_token_timestamp_generation",
-                    "trace": "(line 2938)  Failed: (subprocess)"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_forced_decoder_ids",
-                    "trace": "(line 2938)  Failed: (subprocess)"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_prompt_ids",
-                    "trace": "(line 2938)  Failed: (subprocess)"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_prompt_ids_task_language",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_language_detection",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_generation_multilingual",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_logits_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_en_logits_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_token_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_speculative_decoding_distil",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_speculative_decoding_non_distil",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_en_batched_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_en_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_logits_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_specaugment_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_static_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_static_generation_long_form",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_token_timestamp_batch_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_token_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_token_timestamp_generation_longform",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_empty_longform",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_no_speech_detection",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_prompt_ids",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_single_batch",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_single_batch_beam",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_single_batch_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_multi_batch_hard_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                }
-            ],
-            "multi": [
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_multi_gpu_data_parallel_forward",
-                    "trace": "(line 2938)  Failed: (subprocess)"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_distil_token_timestamp_generation",
-                    "trace": "(line 2938)  Failed: (subprocess)"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_forced_decoder_ids",
-                    "trace": "(line 2938)  Failed: (subprocess)"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_prompt_ids",
-                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_generate_with_prompt_ids_task_language",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_language_detection",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_generation_multilingual",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_logits_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_en_logits_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_token_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_speculative_decoding_distil",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_speculative_decoding_non_distil",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_en_batched_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_en_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_logits_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_specaugment_librispeech",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_static_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_static_generation_long_form",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_token_timestamp_batch_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_token_timestamp_generation",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_token_timestamp_generation_longform",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_empty_longform",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_empty_longform_multi_gpu",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_no_speech_detection",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_prompt_ids",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_single_batch",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_single_batch_beam",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_single_batch_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_multi_batch_hard_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond",
-                    "trace": "(line 172)  ImportError: To support decoding audio data, please install 'torchcodec'."
-                }
-            ]
-        },
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301330636",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712966867/job/47301329883"
-        }
-    }
-}

sample_nvidia.json

@@ -1,1475 +0,0 @@
-{
-    "models_auto": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 226,
-        "skipped": 10,
-        "time_spent": "3.79, 5.93, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215208",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215147"
-        }
-    },
-    "models_bert": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 527,
-        "skipped": 211,
-        "time_spent": "0:01:47, 0:01:50, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215196",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215175"
-        }
-    },
-    "models_clip": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 660,
-        "skipped": 934,
-        "time_spent": "0:02:15, 0:02:11, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215674",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215699"
-        }
-    },
-    "models_detr": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 177,
-        "skipped": 271,
-        "time_spent": "0:01:07, 0:01:11, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216030",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216008"
-        }
-    },
-    "models_gemma3": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 507,
-        "skipped": 320,
-        "time_spent": "0:09:30, 0:09:28, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_model_parallelism",
-                    "trace": "(line 925)  RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!"
-                }
-            ]
-        },
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216642",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216593"
-        }
-    },
-    "models_gemma3n": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 288,
-        "skipped": 703,
-        "time_spent": "0:02:15, 0:02:15, ",
-        "failures": {
-            "single": [
-                {
-                    "line": "tests/models/gemma3n/test_modeling_gemma3n.py::Gemma3nTextModelTest::test_sdpa_padding_matches_padding_free_with_position_ids",
-                    "trace": "(line 4243)  AssertionError: Tensor-likes are not close!"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216605",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216660"
-        }
-    },
-    "models_got_ocr2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 257,
-        "skipped": 333,
-        "time_spent": "0:01:49, 0:01:49, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216911",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216742"
-        }
-    },
-    "models_gpt2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 487,
-        "skipped": 229,
-        "time_spent": "0:02:11, 0:02:01, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216717",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216759"
-        }
-    },
-    "models_internvl": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 355,
-        "skipped": 241,
-        "time_spent": "0:04:33, 0:04:31, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_flex_attention_with_grads",
-                    "trace": "(line 439)  torch._inductor.exc.InductorError: RuntimeError: No valid triton configs. OutOfResources: out of resource: shared memory, Required: 106496, Hardware limit: 101376. Reducing block sizes or `num_stages` may help."
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/internvl/test_modeling_internvl.py::InternVLModelTest::test_flex_attention_with_grads",
-                    "trace": "(line 439)  torch._inductor.exc.InductorError: RuntimeError: No valid triton configs. OutOfResources: out of resource: shared memory, Required: 106496, Hardware limit: 101376. Reducing block sizes or `num_stages` may help."
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217017",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217056"
-        }
-    },
-    "models_llama": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 481,
-        "skipped": 253,
-        "time_spent": "0:03:43, 0:03:37, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217239",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217242"
-        }
-    },
-    "models_llava": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 349,
-        "skipped": 159,
-        "time_spent": "0:08:59, 0:09:11, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217250",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217263"
-        }
-    },
-    "models_mistral3": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 283,
-        "skipped": 267,
-        "time_spent": "0:09:53, 0:09:40, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215108",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215124"
-        }
-    },
-    "models_modernbert": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 174,
-        "skipped": 218,
-        "time_spent": "0:01:27, 0:01:24, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215158",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215123"
-        }
-    },
-    "models_qwen2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 443,
-        "skipped": 251,
-        "time_spent": "0:02:16, 0:02:16, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215909",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215891"
-        }
-    },
-    "models_qwen2_5_omni": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 278,
-        "skipped": 159,
-        "time_spent": "0:02:55, 0:03:00, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/qwen2_5_omni/test_modeling_qwen2_5_omni.py::Qwen2_5OmniThinkerForConditionalGenerationModelTest::test_model_parallelism",
-                    "trace": "(line 675)  AssertionError: Items in the second set but not the first:"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215907",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215896"
-        }
-    },
-    "models_qwen2_5_vl": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 1
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 309,
-        "skipped": 141,
-        "time_spent": "0:03:13, 0:03:14, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
-                    "trace": "(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/qwen2_5_vl/test_modeling_qwen2_5_vl.py::Qwen2_5_VLIntegrationTest::test_small_model_integration_test_batch_different_resolutions",
-                    "trace": "(line 675)  AssertionError: Lists differ: ['sys[314 chars]ion\\n addCriterion\\n\\n addCriterion\\n\\n addCri[75 chars]n\\n'] != ['sys[314 chars]ion\\nThe dog in the picture appears to be a La[81 chars] is']"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215945",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301215911"
-        }
-    },
-    "models_smolvlm": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 497,
-        "skipped": 269,
-        "time_spent": "0:01:33, 0:01:36, ",
-        "failures": {},
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216282",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216321"
-        }
-    },
-    "models_t5": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 1,
-                "multi": 2
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 592,
-        "skipped": 535,
-        "time_spent": "0:03:13, 0:02:52, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelTest::test_multi_gpu_data_parallel_forward",
-                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
-                },
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
-                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/t5/test_modeling_t5.py::T5ModelIntegrationTests::test_export_t5_summarization",
-                    "trace": "(line 687)  AttributeError: 'dict' object has no attribute 'batch_size'"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216565",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216464"
-        }
-    },
-    "models_vit": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 217,
-        "skipped": 199,
-        "time_spent": "2.03, 1.28, ",
-        "failures": {},
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216869",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216833"
-        }
-    },
-    "models_wav2vec2": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 4,
-                "multi": 4
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 672,
-        "skipped": 438,
-        "time_spent": "0:03:37, 0:03:36, ",
-        "failures": {
-            "multi": [
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_inference_mms_1b_all",
-                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
-                },
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm",
-                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
-                },
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_invalid_pool",
-                    "trace": "(line 675)  AssertionError: Traceback (most recent call last):"
-                },
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_pool",
-                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
-                }
-            ],
-            "single": [
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_inference_mms_1b_all",
-                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
-                },
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm",
-                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
-                },
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_invalid_pool",
-                    "trace": "(line 675)  AssertionError: Traceback (most recent call last):"
-                },
-                {
-                    "line": "tests/models/wav2vec2/test_modeling_wav2vec2.py::Wav2Vec2ModelIntegrationTest::test_wav2vec2_with_lm_pool",
-                    "trace": "(line 989)  RuntimeError: Dataset scripts are no longer supported, but found common_voice_11_0.py"
-                }
-            ]
-        },
-        "job_link": {
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216956",
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216929"
-        }
-    },
-    "models_whisper": {
-        "failed": {
-            "PyTorch": {
-                "unclassified": 0,
-                "single": 5,
-                "multi": 6
-            },
-            "TensorFlow": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Flax": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Tokenizers": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Pipelines": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Trainer": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "ONNX": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Auto": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Quantization": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            },
-            "Unclassified": {
-                "unclassified": 0,
-                "single": 0,
-                "multi": 0
-            }
-        },
-        "errors": 0,
-        "success": 1014,
-        "skipped": 475,
-        "time_spent": "0:11:09, 0:11:47, ",
-        "failures": {
-            "single": [
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual",
-                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation",
-                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation",
-                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard",
-                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[272 chars]ting of classics, Sicilian, nade door variatio[8147 chars]le!'] != [\" Fo[272 chars]ting a classic Sicilian, nade door variation o[8150 chars]le!']"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond",
-                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[268 chars]ating, so soft, it would make JD power and her[196 chars]ke.\"] != [\" Fo[268 chars]ating so soft, it would make JD power and her [195 chars]ke.\"]"
-                }
-            ],
-            "multi": [
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelTest::test_multi_gpu_data_parallel_forward",
-                    "trace": "(line 131)  TypeError: EncoderDecoderCache.__init__() missing 1 required positional argument: 'cross_attention_cache'"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_large_batched_generation_multilingual",
-                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_small_longform_timestamps_generation",
-                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_tiny_longform_timestamps_generation",
-                    "trace": "(line 756)  RuntimeError: The frame has 0 channels, expected 1. If you are hitting this, it may be because you are using a buggy FFmpeg version. FFmpeg4 is known to fail here in some valid scenarios. Try to upgrade FFmpeg?"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_longform_multi_batch_hard",
-                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[272 chars]ting of classics, Sicilian, nade door variatio[8147 chars]le!'] != [\" Fo[272 chars]ting a classic Sicilian, nade door variation o[8150 chars]le!']"
-                },
-                {
-                    "line": "tests/models/whisper/test_modeling_whisper.py::WhisperModelIntegrationTests::test_whisper_shortform_single_batch_prev_cond",
-                    "trace": "(line 675)  AssertionError: Lists differ: [\" Fo[268 chars]ating, so soft, it would make JD power and her[196 chars]ke.\"] != [\" Fo[268 chars]ating so soft, it would make JD power and her [195 chars]ke.\"]"
-                }
-            ]
-        },
-        "job_link": {
-            "single": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301216943",
-            "multi": "https://github.com/huggingface/transformers/actions/runs/16712955100/job/47301217012"
-        }
-    }
-}

styles.css

@@ -1,6 +1,7 @@
 /* Global dark theme with configurable margins */
 :root {
     --main-content-bottom-margin: 10px; /* Configurable bottom margin for main content */
+    --plot-padding: 10%; /* Configurable padding for plot centering in percent */
 }
 
 .gradio-container {
@@ -376,6 +377,12 @@ div[data-testid="column"]:has(.sidebar) {
     transition: opacity 0.6s ease-in-out !important;
     flex: 1 1 auto !important;
     min-height: 0 !important;
+    overflow: hidden !important;
+    padding: var(--plot-padding) !important;
+    box-sizing: border-box !important;
+    display: flex !important;
+    justify-content: center !important;
+    align-items: center !important;
 }
 
 /* Plot container scrollbar removed - using overflow: hidden */
@@ -384,15 +391,25 @@ div[data-testid="column"]:has(.sidebar) {
 .gr-plot {
     background-color: #000000 !important;
     transition: opacity 0.6s ease-in-out !important;
+    width: 100% !important;
+    height: 100% !important;
+    display: flex !important;
+    justify-content: center !important;
+    align-items: center !important;
 }
 
 .gr-plot .gradio-plot {
     background-color: #000000 !important;
     transition: opacity 0.6s ease-in-out !important;
+    width: 100% !important;
+    height: 100% !important;
 }
 
 .gr-plot img {
     transition: opacity 0.6s ease-in-out !important;
+    max-width: 100% !important;
+    max-height: 100% !important;
+    object-fit: contain !important;
 }
 
 /* Target the plot wrapper */

summary_page.py

@@ -1,208 +0,0 @@
-import pandas as pd
-from data import extract_model_data
-import matplotlib.pyplot as plt
-
-# Layout parameters
-COLUMNS = 3
-
-# Derived constants
-COLUMN_WIDTH = 100 / COLUMNS  # Each column takes 25% of width
-BAR_WIDTH = COLUMN_WIDTH * 0.8  # 80% of column width for bars
-BAR_MARGIN = COLUMN_WIDTH * 0.1  # 10% margin on each side
-
-# Figure dimensions
-FIGURE_WIDTH = 22  # Wider to accommodate columns and legend
-MAX_HEIGHT = 14  # Maximum height in inches
-MIN_HEIGHT_PER_ROW = 2.8
-FIGURE_PADDING = 1
-
-# Bar styling
-BAR_HEIGHT_RATIO = 0.22  # Bar height as ratio of vertical spacing
-VERTICAL_SPACING_RATIO = 0.2  # Base vertical position ratio
-AMD_BAR_OFFSET = 0.25  # AMD bar offset ratio
-NVIDIA_BAR_OFFSET = 0.54  # NVIDIA bar offset ratio
-
-# Colors
-COLORS = {
-    'passed': '#4CAF50',
-    'failed': '#E53E3E',
-    'skipped': '#FFD54F',
-    'error': '#8B0000',
-    'empty': "#5B5B5B"
-}
-
-# Font styling
-MODEL_NAME_FONT_SIZE = 16
-LABEL_FONT_SIZE = 14
-LABEL_OFFSET = 1  # Distance of label from bar
-FAILURE_RATE_FONT_SIZE = 28
-
-
-def draw_text_and_bar(
-    label: str,
-    stats: dict[str, int],
-    y_bar: float,
-    column_left_position: float,
-    bar_height: float,
-    ax,
-) -> None:
-    """Draw a horizontal bar chart for given stats and its label on the left."""
-    # Text
-    label_x = column_left_position - LABEL_OFFSET
-    failures_present = any(stats[category] > 0 for category in ['failed', 'error'])
-    if failures_present:
-        props = dict(boxstyle='round', facecolor=COLORS['failed'], alpha=0.35)
-    else:
-        props = dict(alpha=0)
-    ax.text(
-        label_x, y_bar, label, ha='right', va='center', color='#CCCCCC', fontsize=LABEL_FONT_SIZE,
-        fontfamily='monospace', fontweight='normal', bbox=props
-    )
-    # Bar
-    total = sum(stats.values())
-    if total > 0:
-        left = column_left_position
-        for category in ['passed', 'failed', 'skipped', 'error']:
-            if stats[category] > 0:
-                width = stats[category] / total * BAR_WIDTH
-                ax.barh(y_bar, width, left=left, height=bar_height, color=COLORS[category], alpha=0.9)
-                left += width
-    else:
-        ax.barh(y_bar, BAR_WIDTH, left=column_left_position, height=bar_height, color=COLORS['empty'], alpha=0.9)
-
-def create_summary_page(df: pd.DataFrame, available_models: list[str]):
-    """Create a summary page with model names and both AMD/NVIDIA test stats bars."""
-    return None
-
-    # Calculate overall failure rates
-    amd_counts, nvidia_counts = get_overall_stats(df, available_models)
-
-    amd_failure_rate = (amd_counts[1] / sum(amd_counts)) if sum(amd_counts) > 0 else 0.0
-    amd_failure_rate *= 100
-    nvidia_failure_rate = (nvidia_counts[1] / sum(nvidia_counts)) if sum(nvidia_counts) > 0 else 0.0
-    nvidia_failure_rate *= 100
-
-    # Calculate dimensions for N-column layout
-    model_count = len(available_models)
-    rows = (model_count + COLUMNS - 1) // COLUMNS  # Ceiling division
-
-    # Figure dimensions - wider for columns, height based on rows
-    height_per_row = min(MIN_HEIGHT_PER_ROW, MAX_HEIGHT / max(rows, 1))
-    figure_height = min(MAX_HEIGHT, rows * height_per_row + FIGURE_PADDING)
-
-    fig = plt.figure(figsize=(FIGURE_WIDTH, figure_height), facecolor='#000000')
-    ax = fig.add_subplot(111)
-    ax.set_facecolor('#000000')
-    
-    # Add overall failure rates at the top as a proper title
-    failure_text = f"Overall Failure Rates: AMD {amd_failure_rate:.1f}%  |  NVIDIA {nvidia_failure_rate:.1f}%"
-    ax.text(50, -1.25, failure_text, ha='center', va='top', 
-           color='#FFFFFF', fontsize=FAILURE_RATE_FONT_SIZE,
-           fontfamily='monospace', fontweight='bold')
-
-    visible_model_count = 0
-    max_y = 0
-
-    for i, model_name in enumerate(available_models):
-        if model_name not in df.index:
-            continue
-
-        row = df.loc[model_name]
-
-        # Extract and process model data
-        amd_stats, nvidia_stats = extract_model_data(row)[:2]
-
-        # Calculate position in 4-column grid
-        col = visible_model_count % COLUMNS
-        row = visible_model_count // COLUMNS
-
-        # Calculate horizontal position for this column
-        col_left = col * COLUMN_WIDTH + BAR_MARGIN
-        col_center = col * COLUMN_WIDTH + COLUMN_WIDTH / 2
-
-        # Calculate vertical position for this row - start from top
-        vertical_spacing = height_per_row
-        y_base = (VERTICAL_SPACING_RATIO + row) * vertical_spacing
-        y_model_name = y_base    # Model name above AMD bar
-        y_amd_bar = y_base + vertical_spacing * AMD_BAR_OFFSET       # AMD bar
-        y_nvidia_bar = y_base + vertical_spacing * NVIDIA_BAR_OFFSET    # NVIDIA bar
-        max_y = max(max_y, y_nvidia_bar + vertical_spacing * 0.3)
-
-        # Model name centered above the bars in this column
-        ax.text(col_center, y_model_name, model_name.lower(),
-               ha='center', va='center', color='#FFFFFF',
-               fontsize=MODEL_NAME_FONT_SIZE, fontfamily='monospace', fontweight='bold')
-
-        # AMD label and bar in this column
-        bar_height = min(0.4, vertical_spacing * BAR_HEIGHT_RATIO)
-        # Draw AMD bar
-        draw_text_and_bar("amd", amd_stats, y_amd_bar, col_left, bar_height, ax)
-        # Draw NVIDIA bar
-        draw_text_and_bar("nvidia", nvidia_stats, y_nvidia_bar, col_left, bar_height, ax)
-
-        # Increment counter for next visible model
-        visible_model_count += 1
-
-
-    # Add AMD and NVIDIA test totals in the bottom left
-    # Calculate line spacing to align middle with legend
-    line_height = 0.4  # Height between lines
-    legend_y = max_y + 1
-
-    # Position the two lines so their middle aligns with legend_y
-    amd_y = legend_y - line_height / 2
-    nvidia_y = legend_y + line_height / 2
-
-    amd_totals_text =    f"AMD Tests    - Passed: {amd_counts[0]}, Failed: {amd_counts[1]}, Skipped: {amd_counts[2]}"
-    nvidia_totals_text = f"NVIDIA Tests - Passed: {nvidia_counts[0]}, Failed: {nvidia_counts[1]}, Skipped: {nvidia_counts[2]}"
-
-    ax.text(0, amd_y, amd_totals_text,
-           ha='left', va='bottom', color='#CCCCCC',
-           fontsize=14, fontfamily='monospace')
-
-    ax.text(0, nvidia_y, nvidia_totals_text,
-           ha='left', va='bottom', color='#CCCCCC',
-           fontsize=14, fontfamily='monospace')
-
-    # Add legend horizontally in bottom right corner
-    patch_height = 0.3
-    patch_width = 3
-
-    legend_start_x = 68.7
-    legend_y = max_y + 1
-    legend_spacing = 10
-    legend_font_size = 15
-
-    # Legend entries
-    legend_items = [
-        ('passed', 'Passed'),
-        ('failed', 'Failed'), 
-        ('skipped', 'Skipped'),
-    ]
-    
-    for i, (status, label) in enumerate(legend_items):
-        x_pos = legend_start_x + i * legend_spacing
-        # Small colored square
-        ax.add_patch(plt.Rectangle((x_pos - 0.6, legend_y), patch_width, -patch_height,
-                                 facecolor=COLORS[status], alpha=0.9))
-        # Status label
-        ax.text(x_pos + patch_width, legend_y, label, 
-               ha='left', va='bottom', color='#CCCCCC', 
-               fontsize=legend_font_size, fontfamily='monospace')
-
-    # Style the axes to be completely invisible and span full width
-    ax.set_xlim(-5, 105)  # Slightly wider to accommodate labels
-    ax.set_ylim(0, max_y + 1)  # Add some padding at the top for title
-    ax.set_xlabel('')
-    ax.set_ylabel('')
-    ax.spines['bottom'].set_visible(False)
-    ax.spines['left'].set_visible(False)
-    ax.spines['top'].set_visible(False)
-    ax.spines['right'].set_visible(False)
-    ax.set_xticks([])
-    ax.set_yticks([])
-    ax.yaxis.set_inverted(True)
-
-    # Remove all margins to make figure stick to top
-    plt.tight_layout()
-    return fig