[Attention][DSA] Enable W4A16 DSA (#51724)
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
This commit is contained in:
+2
-1
@@ -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}).")
|
||||
|
||||
Reference in New Issue
Block a user