[Bugfix][CI/Build] Fix docker build where CUDA archs < 7.0 are being detected (#9254)

CMakeLists.txt

@@ -144,27 +144,32 @@ else()
 endif()
 
 
-#
-# For cuda we want to be able to control which architectures we compile for on 
-# a per-file basis in order to cut down on compile time. So here we extract
-# the set of architectures we want to compile for and remove the from the 
-# CMAKE_CUDA_FLAGS so that they are not applied globally.
-#
 if(VLLM_GPU_LANG STREQUAL "CUDA")
+  #
+  # For cuda we want to be able to control which architectures we compile for on 
+  # a per-file basis in order to cut down on compile time. So here we extract
+  # the set of architectures we want to compile for and remove the from the 
+  # CMAKE_CUDA_FLAGS so that they are not applied globally.
+  #
   clear_cuda_arches(CUDA_ARCH_FLAGS)
   extract_unique_cuda_archs_ascending(CUDA_ARCHS "${CUDA_ARCH_FLAGS}")
   message(STATUS "CUDA target architectures: ${CUDA_ARCHS}")
+  # Filter the target architectures by the supported supported archs
+  # since for some files we will build for all CUDA_ARCHS.
+  cuda_archs_loose_intersection(CUDA_ARCHS 
+    "${CUDA_SUPPORTED_ARCHS}" "${CUDA_ARCHS}")
+  message(STATUS "CUDA supported target architectures: ${CUDA_ARCHS}")
+else()
+  #
+  # For other GPU targets override the GPU architectures detected by cmake/torch
+  # and filter them by the supported versions for the current language.
+  # The final set of arches is stored in `VLLM_GPU_ARCHES`.
+  #
+  override_gpu_arches(VLLM_GPU_ARCHES
+    ${VLLM_GPU_LANG}
+    "${${VLLM_GPU_LANG}_SUPPORTED_ARCHS}")
 endif()
 
-#
-# Override the GPU architectures detected by cmake/torch and filter them by
-# the supported versions for the current language.
-# The final set of arches is stored in `VLLM_GPU_ARCHES`.
-#
-override_gpu_arches(VLLM_GPU_ARCHES
-  ${VLLM_GPU_LANG}
-  "${${VLLM_GPU_LANG}_SUPPORTED_ARCHS}")
-
 #
 # Query torch for additional GPU compilation flags for the given
 # `VLLM_GPU_LANG`.