[Perf][Kernel] Integrate DeepSelect TopK for the DSA sparse indexer (#56464)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com> Signed-off-by: Roger Wang <hey@rogerw.io> Co-authored-by: Kimi Code <noreply@moonshot.ai> Co-authored-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
co-authored by
Kimi Code
Roger Wang
parent
1cfd972816
commit
fa008bdccf
@@ -1015,6 +1015,7 @@ class precompiled_wheel_utils:
|
||||
"vllm/_flashmla_extension_C.abi3.so",
|
||||
"vllm/_flashkda_C.abi3.so",
|
||||
"vllm/_sparse_flashmla_C.abi3.so",
|
||||
"vllm/_deepselect_C.abi3.so",
|
||||
"vllm/vllm_flash_attn/_vllm_fa2_C.abi3.so",
|
||||
"vllm/vllm_flash_attn/_vllm_fa3_C.abi3.so",
|
||||
"vllm/cumem_allocator.abi3.so",
|
||||
@@ -1381,6 +1382,9 @@ if _is_cuda():
|
||||
ext_modules.append(
|
||||
CMakeExtension(name="vllm._flashmla_extension_C", optional=True)
|
||||
)
|
||||
# DeepSelect requires CUDA 12.9 or later (SM100a/SM103a only)
|
||||
# Optional since it won't build on unsupported architectures
|
||||
ext_modules.append(CMakeExtension(name="vllm._deepselect_C", optional=True))
|
||||
if USE_PRECOMPILED_EXTENSIONS or (
|
||||
CUDA_HOME and get_nvcc_cuda_version() >= Version("12.0")
|
||||
):
|
||||
|
||||
Reference in New Issue
Block a user