[Kernel][Model] Varlen prefill + Prefill chunking support for mamba kernels and Jamba model (#8533)

This commit is contained in:
Mor Zusman
2024-09-29 17:35:58 -04:00
committed by GitHub
parent 6c9ba48fde
commit f13a07b1f8
13 changed files with 1176 additions and 894 deletions
+18 -13
View File
@@ -215,25 +215,30 @@ void moe_align_block_size(torch::Tensor topk_ids, int64_t num_experts,
torch::Tensor experts_ids,
torch::Tensor num_tokens_post_pad);
std::vector<torch::Tensor> selective_scan_fwd(
const torch::Tensor& u, const torch::Tensor& delta, const torch::Tensor& A,
const torch::Tensor& B, const torch::Tensor& C,
const c10::optional<torch::Tensor>& D_,
const c10::optional<torch::Tensor>& z_,
const c10::optional<torch::Tensor>& delta_bias_, bool delta_softplus,
const c10::optional<torch::Tensor>& index_,
const c10::optional<torch::Tensor>& x);
void selective_scan_fwd(const torch::Tensor& u, const torch::Tensor& delta,
const torch::Tensor& A, const torch::Tensor& B,
const torch::Tensor& C,
const c10::optional<torch::Tensor>& D_,
const c10::optional<torch::Tensor>& z_,
const c10::optional<torch::Tensor>& delta_bias_,
bool delta_softplus,
const c10::optional<torch::Tensor>& query_start_loc,
const c10::optional<torch::Tensor>& cache_indices,
const c10::optional<torch::Tensor>& has_initial_state,
const torch::Tensor& ssm_states);
at::Tensor causal_conv1d_update(
const at::Tensor& x, const at::Tensor& conv_state, const at::Tensor& weight,
const c10::optional<at::Tensor>& bias, bool silu_activation,
const c10::optional<at::Tensor>& conv_state_indices);
const c10::optional<at::Tensor>& bias_, bool silu_activation,
const c10::optional<at::Tensor>& cache_seqlens_,
const c10::optional<at::Tensor>& conv_state_indices_);
at::Tensor causal_conv1d_fwd(const at::Tensor& x, const at::Tensor& weight,
const c10::optional<at::Tensor>& bias_,
const c10::optional<at::Tensor>& seq_idx_,
const c10::optional<at::Tensor>& initial_states_,
const c10::optional<at::Tensor>& final_states_out_,
const c10::optional<at::Tensor>& conv_states,
const c10::optional<at::Tensor>& query_start_loc,
const c10::optional<at::Tensor>& cache_indices,
const c10::optional<at::Tensor>& has_initial_state,
bool silu_activation);
#ifndef USE_ROCM