[CPU] Conv1d optimised kernel for aarch64 (#54093)

Signed-off-by: Anna Mayne <anna.mayne@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
almayne
2026-09-30 20:23:42 +08:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent df5668e5c9
commit 93dd80f636
9 changed files with 460 additions and 205 deletions
+29 -20
View File
@@ -281,14 +281,14 @@ at::Tensor causal_conv1d_fwd_cpu(
const std::optional<at::Tensor>& query_start_loc,
const std::optional<at::Tensor>& cache_indices,
const std::optional<at::Tensor>& has_initial_state, bool silu_activation,
int64_t pad_slot_id, bool is_vnni);
int64_t pad_slot_id, bool is_weight_packed);
at::Tensor causal_conv1d_update_cpu(
const at::Tensor& x, const at::Tensor& conv_states,
const at::Tensor& weight, const std::optional<at::Tensor>& bias,
bool silu_activation, const std::optional<at::Tensor>& num_accepted_tokens,
const std::optional<at::Tensor>& conv_state_indices, int64_t pad_slot_id,
bool is_vnni);
bool is_weight_packed);
void activation_lut_bf16(torch::Tensor& out, torch::Tensor& input,
const std::string& activation);
@@ -517,6 +517,33 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
#endif // (defined(__aarch64__) && !defined(__APPLE__))
#if (defined(__aarch64__) && defined(ARM_BF16_SUPPORT) && \
!defined(__APPLE__)) || \
(defined(__AVX512BF16__) && defined(__AVX512F__) && \
defined(__AVX512VNNI__))
// 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_weight_packed) -> "
"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? num_accepted_tokens, Tensor? conv_state_indices, int "
"pad_slot_id, "
"bool is_weight_packed) -> Tensor");
ops.impl("causal_conv1d_update_cpu", torch::kCPU, &causal_conv1d_update_cpu);
#endif
// Layernorm
// Apply Root Mean Square (RMS) Normalization to the input tensor.
ops.def(
@@ -665,24 +692,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
"-> (Tensor, Tensor)");
ops.impl("quantize_fp8e4m3_vec", torch::kCPU, &quantize_fp8e4m3_vec);
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? num_accepted_tokens, Tensor? conv_state_indices, int "
"pad_slot_id, "
"bool is_vnni) -> Tensor");
ops.impl("causal_conv1d_update_cpu", torch::kCPU, &causal_conv1d_update_cpu);
// Adapted from sglang: MLA CPU kernels (AMX-only, DeepSeek V2/V3/R1)
ops.def(
"decode_attention_cpu(Tensor query, Tensor k_buffer, Tensor v_buffer, "