[CPU][Perf] Enable fused kernels for GDN's gated delta rules (#43534)

Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
Fadi Arafeh
2026-06-02 08:00:48 +00:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent dcdfe66bfa
commit 0b25cf4419
11 changed files with 824 additions and 597 deletions
+19 -19
View File
@@ -447,6 +447,25 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
"bool is_vnni) -> Tensor");
ops.impl("fp8_scaled_mm_cpu", torch::kCPU, &fp8_scaled_mm_cpu);
// Adapted from sglang: casual_conv1d kernels
ops.def("causal_conv1d_weight_pack(Tensor weight) -> Tensor");
ops.impl("causal_conv1d_weight_pack", torch::kCPU,
&causal_conv1d_weight_pack);
ops.def(
"causal_conv1d_fwd_cpu(Tensor x, Tensor weight, Tensor? bias, Tensor? "
"conv_states, Tensor? query_start_loc,"
"Tensor? cache_indices, Tensor? has_initial_state, bool silu_activation, "
"int pad_slot_id, bool is_vnni) -> "
"Tensor");
ops.impl("causal_conv1d_fwd_cpu", torch::kCPU, &causal_conv1d_fwd_cpu);
ops.def(
"causal_conv1d_update_cpu(Tensor x, Tensor(a!) conv_states, Tensor "
"weight, Tensor? bias, bool silu_activation,"
"Tensor? cache_seqlens, Tensor? conv_state_indices, int pad_slot_id, "
"bool is_vnni) -> Tensor");
ops.impl("causal_conv1d_update_cpu", torch::kCPU, &causal_conv1d_update_cpu);
#endif
// Adapted from sglang: GDN kernels
ops.def(
"chunk_gated_delta_rule_cpu(Tensor query, Tensor key, Tensor value, "
@@ -470,25 +489,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
"-> (Tensor, Tensor)");
ops.impl("fused_gdn_gating_cpu", torch::kCPU, &fused_gdn_gating_cpu);
// Adapted from sglang: casual_conv1d kernels
ops.def("causal_conv1d_weight_pack(Tensor weight) -> Tensor");
ops.impl("causal_conv1d_weight_pack", torch::kCPU,
&causal_conv1d_weight_pack);
ops.def(
"causal_conv1d_fwd_cpu(Tensor x, Tensor weight, Tensor? bias, Tensor? "
"conv_states, Tensor? query_start_loc,"
"Tensor? cache_indices, Tensor? has_initial_state, bool silu_activation, "
"int pad_slot_id, bool is_vnni) -> "
"Tensor");
ops.impl("causal_conv1d_fwd_cpu", torch::kCPU, &causal_conv1d_fwd_cpu);
ops.def(
"causal_conv1d_update_cpu(Tensor x, Tensor(a!) conv_states, Tensor "
"weight, Tensor? bias, bool silu_activation,"
"Tensor? cache_seqlens, Tensor? conv_state_indices, int pad_slot_id, "
"bool is_vnni) -> Tensor");
ops.impl("causal_conv1d_update_cpu", torch::kCPU, &causal_conv1d_update_cpu);
#endif
// CPU attention kernels
ops.def(
"get_scheduler_metadata(int num_req, int num_heads_q, int num_heads_kv, "