Synchronizing local compiler cache.

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/stable-diffusion/stabilityai/sdxl-turbo/7c0a3faa643571c6da59.json

@@ -0,0 +1,170 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/sdxl-turbo",
+  "_task": null,
+  "text_encoder": {
+    "architectures": [
+      "CLIPTextModel"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "export_model_type": "clip-text-model",
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "clip_text_model",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": false,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_sequence_length": 77,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "output_hidden_states": true,
+    "vocab_size": 49408
+  },
+  "text_encoder_2": {
+    "architectures": [
+      "CLIPTextModelWithProjection"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "export_model_type": "clip-text-with-projection",
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "clip_text_model",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": false,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_sequence_length": 77,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32,
+    "output_hidden_states": true,
+    "vocab_size": 49408
+  },
+  "unet": {
+    "_class_name": "UNet2DConditionModel",
+    "act_fn": "silu",
+    "addition_embed_type": "text_time",
+    "addition_embed_type_num_heads": 64,
+    "addition_time_embed_dim": 256,
+    "attention_head_dim": [
+      5,
+      10,
+      20
+    ],
+    "attention_type": "default",
+    "block_out_channels": [
+      320,
+      640,
+      1280
+    ],
+    "center_input_sample": false,
+    "class_embed_type": null,
+    "class_embeddings_concat": false,
+    "conv_in_kernel": 3,
+    "conv_out_kernel": 3,
+    "cross_attention_dim": 2048,
+    "cross_attention_norm": null,
+    "down_block_types": [
+      "DownBlock2D",
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D"
+    ],
+    "downsample_padding": 1,
+    "dropout": 0.0,
+    "dual_cross_attention": false,
+    "encoder_hid_dim": null,
+    "encoder_hid_dim_type": null,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 4,
+    "layers_per_block": 2,
+    "mid_block_only_cross_attention": null,
+    "mid_block_scale_factor": 1,
+    "mid_block_type": "UNetMidBlock2DCrossAttn",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_height": 128,
+      "static_num_channels": 4,
+      "static_sequence_length": 77,
+      "static_vae_scale_factor": 8,
+      "static_width": 128,
+      "task": "semantic-segmentation",
+      "tensor_parallel_size": 1
+    },
+    "norm_eps": 1e-05,
+    "norm_num_groups": 32,
+    "num_attention_heads": null,
+    "num_class_embeds": null,
+    "only_cross_attention": false,
+    "out_channels": 4,
+    "projection_class_embeddings_input_dim": 2816,
+    "resnet_out_scale_factor": 1.0,
+    "resnet_skip_time_act": false,
+    "resnet_time_scale_shift": "default",
+    "reverse_transformer_layers_per_block": null,
+    "time_cond_proj_dim": null,
+    "time_embedding_act_fn": null,
+    "time_embedding_dim": null,
+    "time_embedding_type": "positional",
+    "timestep_post_act": null,
+    "transformer_layers_per_block": [
+      1,
+      2,
+      10
+    ],
+    "up_block_types": [
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "UpBlock2D"
+    ],
+    "upcast_attention": null,
+    "use_linear_projection": true
+  }
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec1b2be0f8ee63964af019d80bbfeb9f7563bd5d0a58ef8238eb2aeadeac73a
+oid sha256:9f188fe6e272615f1b0a9b6dea73e30b19fc75411bedefd40ebe293891a0ee9b
 size 496092729

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefacb43051d79d299d6d15149aedec761d0d41dbbeb896fe9773811052679e2
+oid sha256:2412a159046de92aed3174b075ffba9452e6f6107a7ec3dac242f18fa28db8aa
 size 2801582571

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d86a82494c312e169c634ed9b4fe15bff6fe0d52880ec25525f049778bd875
+oid sha256:bc1f5602e925fb8342182ac8d2c538d66e336c3fa6007378be67194e40110d77
 size 4175474813

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/vae_decoder/config.json

@@ -3,12 +3,12 @@
   "_commit_hash": null,
   "_diffusers_version": "0.34.0",
   "_use_default_values": [
-    "use_quant_conv",
+    "latents_mean",
     "use_post_quant_conv",
-    "latents_std",
     "mid_block_add_attention",
+    "use_quant_conv",
     "shift_factor",
-    "latents_mean"
+    "latents_std"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4de3f7f2de9c277ca6756a43c0b2334bfbbe225294b635f4555759afd1fbc3e
+oid sha256:fa5d60e4357d5328326d36235f973693d2e1f728a8f4ca5288297a575210d2c9
 size 370909427

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/vae_encoder/config.json

@@ -3,12 +3,12 @@
   "_commit_hash": null,
   "_diffusers_version": "0.34.0",
   "_use_default_values": [
-    "use_quant_conv",
+    "latents_mean",
     "use_post_quant_conv",
-    "latents_std",
     "mid_block_add_attention",
+    "use_quant_conv",
     "shift_factor",
-    "latents_mean"
+    "latents_std"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f08ffc633ed8ce1e231e83ac3227f6cae46b7b69e6a2761d3103143e84916e7
+oid sha256:326092a57f5d7e585dc2dbfec68f88f97dc6527ff71ccaab6a831d907c9aae86
 size 222984883