[12/n] final _C library kernel migration (#45415)

This commit is contained in:
Chris Leonard
2026-06-19 06:57:26 -07:00
committed by GitHub
parent 69bdd34542
commit b9a7cd464c
17 changed files with 239 additions and 212 deletions
+4 -1
View File
@@ -769,6 +769,7 @@ class precompiled_wheel_utils:
"vllm/_C.abi3.so",
"vllm/_C_stable_libtorch.abi3.so",
"vllm/_moe_C_stable_libtorch.abi3.so",
"vllm/_qutlass_C.abi3.so",
"vllm/_flashmla_C.abi3.so",
"vllm/_flashmla_extension_C.abi3.so",
"vllm/_sparse_flashmla_C.abi3.so",
@@ -1135,6 +1136,7 @@ if _is_cuda():
# DeepGEMM requires CUDA 12.3+ (SM90/SM100)
# Optional since it won't build on unsupported architectures
ext_modules.append(CMakeExtension(name="vllm._deep_gemm_C", optional=True))
ext_modules.append(CMakeExtension(name="vllm._qutlass_C", optional=True))
# fmha_sm100 is a Python/CuTe-DSL package installed into vllm.third_party.
ext_modules.append(CMakeExtension(name="vllm.fmha_sm100", optional=True))
@@ -1149,7 +1151,8 @@ if _is_cpu():
ext_modules.append(CMakeExtension(name="vllm._C"))
if _build_custom_ops():
ext_modules.append(CMakeExtension(name="vllm._C"))
if _is_hip():
ext_modules.append(CMakeExtension(name="vllm._C"))
if _is_cuda() or _is_hip():
ext_modules.append(CMakeExtension(name="vllm._C_stable_libtorch"))
ext_modules.append(CMakeExtension(name="vllm._moe_C_stable_libtorch"))