Hugging Face's logo

lukealonso
/
MiniMax-M2-NVFP4

Safetensors
minimax
8-bit precision
modelopt
Model card Files
xet
Community
2
lukealonso commited on
Commit
20886f2
·
verified ·
1 Parent(s): 91e9bef

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -39,7 +39,7 @@ CUDA_VISIBLE_DEVICES=${CUDA_VISIBLE_DEVICES:-0,1} /opt/vllm/bin/vllm serve lukea
39
  ```
40
 
41
  ```
42
- My environment:
43
 
44
  Python: 3.12.3
45
  vLLM: 0.11.2.dev360+g8e7a89160
@@ -48,7 +48,8 @@ My environment:
48
  GPU 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition
49
  GPU 1: NVIDIA RTX PRO 6000 Blackwell Workstation Edition
50
  Triton: 3.5.0
51
- FlashInfer: 0.5.3```
 
52
 
53
 
54
  Tested (but not extensively validated) on *2x* RTX Pro 6000 Blackwell via:
 
39
  ```
40
 
41
  ```
42
+ Environment:
43
 
44
  Python: 3.12.3
45
  vLLM: 0.11.2.dev360+g8e7a89160
 
48
  GPU 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition
49
  GPU 1: NVIDIA RTX PRO 6000 Blackwell Workstation Edition
50
  Triton: 3.5.0
51
+ FlashInfer: 0.5.3
52
+ ```
53
 
54
 
55
  Tested (but not extensively validated) on *2x* RTX Pro 6000 Blackwell via: