linzhao-amd commited on
Commit
28bf612
·
verified ·
1 Parent(s): 0364bea

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -158,7 +158,7 @@ The model was evaluated on GSM8K using vLLM and EvalScope.
158
  The following results were obtained using EvalScope and vLLM.
159
 
160
  #### Launching server
161
- We launch the vLLM server following [vLLM Recipes](https://recipes.vllm.ai/MiniMaxAI/MiniMax-M3.1-Flash?hardware=mi355x&variant=mxfp4).
162
  ```bash
163
  VLLM_ROCM_USE_AITER=1 \
164
  VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 \
 
158
  The following results were obtained using EvalScope and vLLM.
159
 
160
  #### Launching server
161
+ We launch the vLLM server using the [vLLM Recipes](https://recipes.vllm.ai/MiniMaxAI/MiniMax-M3.1-Flash?hardware=mi355x&variant=mxfp4) with docker image `vllm/vllm-openai-rocm:minimax-m31-flash`.
162
  ```bash
163
  VLLM_ROCM_USE_AITER=1 \
164
  VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 \