add vllm source code part. (#19)

- add vllm source code part. (ebb38e6711d29dc7208aeee3f522bf2a6023cee0)


Co-authored-by: asher <asherszhang@users.noreply.huggingface.co>

README.md

@@ -266,7 +266,7 @@ docker run --rm  --ipc=host \
         --gpus=all \
         -it \
         -e VLLM_USE_V1=0 \
-        --entrypoint python mirror.ccs.tencentyun.com/hunyuaninfer/hunyuan-large:hunyuan-moe-A13B-vllm \
+        --entrypoint python hunyuaninfer/hunyuan-a13b:hunyuan-moe-A13B-vllm \
         -m vllm.entrypoints.openai.api_server \
         --host 0.0.0.0 \
         --tensor-parallel-size 4 \
@@ -275,6 +275,12 @@ docker run --rm  --ipc=host \
         --trust_remote_code
 ```
 
+### Source Code
+Support for this model has been added via  this [PR 20114](https://github.com/vllm-project/vllm/pull/20114 ) in the vLLM project. 
+
+You can build and run vLLM from source after merging this pull request into your local repository.
+
+
 
 #### Tool Calling with vLLM
 
@@ -296,6 +302,8 @@ These settings enable vLLM to correctly interpret and route tool calls generated
 
 vLLM reasoning parser support on Hunyuan A13B model is under development.
 
+
+
 ### SGLang
 
 #### Docker Image