Skip to content
Closed
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions csrc/torch_bindings.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -130,13 +130,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
") -> ()");
ops.impl("advance_step_flashinfer", torch::kCUDA, &advance_step_flashinfer);

// Compute MLA decode using cutlass.
ops.def(
"cutlass_mla_decode(Tensor! out, Tensor q_nope, Tensor q_pe,"
" Tensor kv_c_and_k_pe_cache, Tensor seq_lens,"
" Tensor page_table, float scale) -> ()");
ops.impl("cutlass_mla_decode", torch::kCUDA, &cutlass_mla_decode);

// Layernorm
// Apply Root Mean Square (RMS) Normalization to the input tensor.
ops.def(
Expand Down Expand Up @@ -361,6 +354,13 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
{stride_tag});
// conditionally compiled so impl registration is in source file

// Compute MLA decode using cutlass.
ops.def(
"cutlass_mla_decode(Tensor! out, Tensor q_nope, Tensor q_pe,"
" Tensor kv_c_and_k_pe_cache, Tensor seq_lens,"
" Tensor page_table, float scale) -> ()");
ops.impl("cutlass_mla_decode", torch::kCUDA, &cutlass_mla_decode);

// CUTLASS nvfp4 block scaled GEMM
ops.def(
"cutlass_scaled_fp4_mm(Tensor! out, Tensor a, Tensor b,"
Expand Down
Loading