[PERF]MiniMax-M2 gate kernel (#38445)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: qianlihuang <91178480+qianlihuang@users.noreply.github.com>
Co-authored-by: Yiliu Dong <91178480+qianlihuang@users.noreply.github.com>
This commit is contained in:
Jee Jee Li
2026-05-29 18:28:34 -07:00
committed by GitHub
co-authored by Yiliu Dong
parent 187457a952
commit 559d6710bf
10 changed files with 716 additions and 23 deletions
+4
View File
@@ -247,6 +247,10 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
ops.def(
"dsv3_fused_a_gemm(Tensor! output, Tensor mat_a, Tensor mat_b) -> ()");
// BF16/FP32 x FP32 -> FP32 router GEMM for H=3072, E=256, M<=32 (SM90+).
// conditionally compiled so impl registration is in source file
ops.def("fp32_router_gemm(Tensor! output, Tensor mat_a, Tensor mat_b) -> ()");
// reorder weight for AllSpark Ampere W8A16 Fused Gemm kernel
ops.def(
"rearrange_kn_weight_as_n32k16_order(Tensor b_qweight, Tensor b_scales, "