[10c/n] Migrate MoE kernels to torch stable ABI (#44565)
Signed-off-by: Chris Leonard <chleonar@redhat.com> Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
This commit is contained in:
co-authored by
Shengqi Chen
parent
2f2c5cf4f1
commit
6e64c1bab1
@@ -246,6 +246,22 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
|
||||
"awq_dequantize(Tensor _kernel, Tensor _scaling_factors, "
|
||||
"Tensor _zeros, SymInt split_k_iters, int thx, int thy) -> Tensor");
|
||||
|
||||
// Expert-specialization mxfp8 blockscaled grouped quantization (SM100+).
|
||||
ops.def(
|
||||
"mxfp8_experts_quant("
|
||||
" Tensor input, Tensor problem_sizes, Tensor expert_offsets,"
|
||||
" Tensor blockscale_offsets, Tensor! quant_output, Tensor! scale_factor)"
|
||||
" -> ()");
|
||||
// conditionally compiled so impl registration is in source file
|
||||
|
||||
// Expert-specialization mxfp8 blockscaled grouped GEMM (SM100+).
|
||||
ops.def(
|
||||
"cutlass_mxfp8_grouped_mm("
|
||||
" Tensor a, Tensor b, Tensor sfa, Tensor sfb, Tensor! out,"
|
||||
" Tensor problem_sizes, Tensor expert_offsets, Tensor blockscale_offsets)"
|
||||
" -> ()");
|
||||
// conditionally compiled so impl registration is in source file
|
||||
|
||||
// DeepSeek V3 fused A GEMM (SM 9.0+, bf16 only, 1-16 tokens).
|
||||
// conditionally compiled so impl registration is in source file
|
||||
ops.def(
|
||||
|
||||
Reference in New Issue
Block a user