Fix bug (#4709)

Author: Bobholamovic

deploy/genai_vllm_server_docker/Dockerfile

@@ -13,7 +13,7 @@ RUN python -m pip install "paddlex${PADDLEX_VERSION}"
 
 ARG BUILD_FOR_SM120=false
 RUN if [ "${BUILD_FOR_SM120}" = 'true' ]; then \
-        python -m pip install torch==2.8.0 https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.3.14/flash_attn-2.8.3+cu128torch2.8-cp310-cp310-linux_x86_64.whl; \
+        python -m pip install torch==2.8.0 https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.4.11/flash_attn-2.8.3%2Bcu128torch2.8-cp310-cp310-linux_x86_64.whl; \
     else \
         python -m pip install torch==2.8.0 https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.3.14/flash_attn-2.8.2+cu128torch2.8-cp310-cp310-linux_x86_64.whl; \
     fi \