[CPU][Spec Decode] Optimize GDN conv path for speculative decoding (#48577)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com> Co-authored-by: Codex <codex@openai.com> Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
co-authored by
Codex
Li, Jiang <jiang1.li@intel.com>
parent
c314af1abf
commit
544cb724c8
@@ -147,7 +147,7 @@ at::Tensor causal_conv1d_fwd_cpu(
|
||||
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>& cache_seqlens,
|
||||
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);
|
||||
|
||||
@@ -516,7 +516,8 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
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, "
|
||||
"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);
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user