[CI/Build] get rid of unused VLLM_FA_CMAKE_GPU_ARCHES (#21599)

Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>

.buildkite/scripts/hardware_ci/run-gh200-test.sh

@@ -16,8 +16,7 @@ DOCKER_BUILDKIT=1 docker build . \
   --build-arg max_jobs=66 \
   --build-arg nvcc_threads=2 \
   --build-arg RUN_WHEEL_CHECK=false \
-  --build-arg torch_cuda_arch_list="9.0+PTX" \
-  --build-arg vllm_fa_cmake_gpu_arches="90-real"
+  --build-arg torch_cuda_arch_list="9.0+PTX"
 
 # Setup cleanup
 remove_docker_container() { docker rm -f gh200-test || true; }

.github/workflows/scripts/build.sh

@@ -15,7 +15,6 @@ $python_executable -m pip install -r requirements/build.txt -r requirements/cuda
 export MAX_JOBS=1
 # Make sure release wheels are built for the following architectures
 export TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
-export VLLM_FA_CMAKE_GPU_ARCHES="80-real;90-real"
 
 bash tools/check_repo.sh
 

docker/Dockerfile

@@ -164,9 +164,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 # see https://github.com/pytorch/pytorch/pull/123243
 ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0 12.0'
 ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
-# Override the arch list for flash-attn to reduce the binary size
-ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
-ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}
 #################### BASE BUILD IMAGE ####################
 
 #################### WHEEL BUILD IMAGE ####################

docker/Dockerfile.nightly_torch

@@ -114,9 +114,6 @@ RUN cat torch_build_versions.txt
 # explicitly set the list to avoid issues with torch 2.2
 # see https://github.com/pytorch/pytorch/pull/123243
 
-# Override the arch list for flash-attn to reduce the binary size
-ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
-ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}
 #################### BASE BUILD IMAGE ####################
 
 #################### WHEEL BUILD IMAGE ####################

docs/deployment/docker.md

@@ -106,8 +106,7 @@ of PyTorch Nightly and should be considered **experimental**. Using the flag `--
     -t vllm/vllm-gh200-openai:latest \
     --build-arg max_jobs=66 \
     --build-arg nvcc_threads=2 \
-    --build-arg torch_cuda_arch_list="9.0 10.0+PTX" \
-    --build-arg vllm_fa_cmake_gpu_arches="90-real"
+    --build-arg torch_cuda_arch_list="9.0 10.0+PTX"
     ```
 
 !!! note