[Feature] Add a fast-topk to sgl-kernel for DeepSeek v3.2 (#11194)

Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
This commit is contained in:
DarkSharpness
2025-10-06 01:19:03 +08:00
committed by GitHub
parent 4cb5a5235e
commit e0b2d3eebe
7 changed files with 588 additions and 1 deletions

View File

@@ -268,6 +268,7 @@ set(SOURCES
"csrc/elementwise/concat_mla.cu"
"csrc/elementwise/fused_add_rms_norm_kernel.cu"
"csrc/elementwise/rope.cu"
"csrc/elementwise/topk.cu"
"csrc/common_extension.cc"
"csrc/gemm/awq_kernel.cu"