[UX] Integrate DeepGEMM into vLLM wheel via CMake (#37980)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Michael Goin
2026-04-09 03:56:32 +02:00
committed by GitHub
parent 83aea2147f
commit eb4205fee5
12 changed files with 251 additions and 40 deletions

3
.gitignore vendored
View File

@@ -12,6 +12,9 @@ vllm/third_party/triton_kernels/*
# FlashMLA interface copied from source
vllm/third_party/flashmla/flash_mla_interface.py
# DeepGEMM vendored package built from source
vllm/third_party/deep_gemm/
# triton jit
.triton