[Bugfix] Flash attention arches not getting set properly (vllm-projec…

…t#9062)

Signed-off-by: Sumit Dubey <sumit.dubey2@ibm.com>

CMakeLists.txt

@@ -482,6 +482,17 @@ if (NOT VLLM_TARGET_DEVICE STREQUAL "cuda")
   return()
 endif ()
 
+# vLLM flash attention requires VLLM_GPU_ARCHES to contain the set of target  
+# arches in the CMake syntax (75-real, 89-virtual, etc), since we clear the 
+# arches in the CUDA case (and instead set the gencodes on a per file basis) 
+# we need to manually set VLLM_GPU_ARCHES here.
+if(VLLM_GPU_LANG STREQUAL "CUDA")
+  foreach(_ARCH ${CUDA_ARCHS})
+    string(REPLACE "." "" _ARCH "${_ARCH}")
+    list(APPEND VLLM_GPU_ARCHES "${_ARCH}-real")
+  endforeach()
+endif()
+
 #
 # Build vLLM flash attention from source
 #