[Perf][GLM-5.2] Blackwell decode optimizations (#48597)
Signed-off-by: Peiyuan Zhou <peiyuanzhou1994@gmail.com> Signed-off-by: zhou <zhou@zhoudeMacBook-Pro.local> Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com> Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: zhou <zhou@zhoudeMacBook-Pro.local> Co-authored-by: stefankoncarevic <Stefan.Koncarevic@amd.com>
This commit is contained in:
co-authored by
Claude
Giancarlo Delfin
Thien Tran
OpenAI Codex
zhou
stefankoncarevic
parent
0d77325b10
commit
dd72658e7d
@@ -330,6 +330,10 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
|
||||
// conditionally compiled so impl registration is in source file
|
||||
ops.def("fp32_router_gemm(Tensor! output, Tensor mat_a, Tensor mat_b) -> ()");
|
||||
|
||||
// BF16 skinny GEMM (M<=32, weight-BW-bound shapes, e.g. MTP eh_proj).
|
||||
// conditionally compiled so impl registration is in source file
|
||||
ops.def("bf16_skinny_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, "
|
||||
|
||||
Reference in New Issue
Block a user