[Attention][DSA] Enable W4A16 DSA (#51724)

Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
This commit is contained in:
sychen52
2026-09-01 12:37:47 +08:00
committed by GitHub
parent ce2e343be1
commit 7c5dc571cb
17 changed files with 824 additions and 22 deletions
+2 -1
View File
@@ -1042,7 +1042,8 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
"csrc/libtorch_stable/quantization/fp4/nvfp4_blockwise_moe_kernel.cu"
"csrc/libtorch_stable/quantization/fp4/mxfp4_experts_quant.cu"
"csrc/libtorch_stable/quantization/fp4/mxfp4_blockwise_moe_kernel.cu"
"csrc/libtorch_stable/nvfp4_kv_cache_kernels.cu")
"csrc/libtorch_stable/nvfp4_kv_cache_kernels.cu"
"csrc/libtorch_stable/nvfp4_ds_mla_cache_kernels.cu")
if(NOT ${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.9)
message(STATUS
"Building mxfp4_experts_quant unsupported stubs because CUDA compiler version is not >= 12.9 (found ${CMAKE_CUDA_COMPILER_VERSION}).")