Unverified Commit 45a1a69b authored by Simon Mo's avatar Simon Mo Committed by GitHub
Browse files

[Build] Disable sm_90a in cu11 (#5141)

parent 87a658c8
......@@ -200,11 +200,13 @@ if(VLLM_GPU_LANG STREQUAL "CUDA")
# The CUTLASS kernels for Hopper require sm90a to be enabled.
# This is done via the below gencode option, BUT that creates kernels for both sm90 and sm90a.
# That adds an extra 17MB to compiled binary, so instead we selectively enable it.
if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER 11)
set_source_files_properties(
"csrc/quantization/cutlass_w8a8/scaled_mm_dq_c3x.cu"
PROPERTIES
COMPILE_FLAGS
"-gencode arch=compute_90a,code=sm_90a")
endif()
endif()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment