[V0 Deprecation] Remove advance_step (#22969)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-08-15 08:22:31 -07:00
committed by GitHub
parent 74f441f4b5
commit 1c859a1387
16 changed files with 9 additions and 892 deletions
-16
View File
@@ -145,22 +145,6 @@ void gelu_fast(torch::Tensor& out, torch::Tensor& input);
void gelu_quick(torch::Tensor& out, torch::Tensor& input);
void advance_step_flashattn(int64_t num_seqs, int64_t num_queries,
int64_t block_size, torch::Tensor& input_tokens,
torch::Tensor& sampled_token_ids,
torch::Tensor& input_positions,
torch::Tensor& seq_lens,
torch::Tensor& slot_mapping,
torch::Tensor& block_tables);
void advance_step_flashinfer(
int64_t num_seqs, int64_t num_queries, int64_t block_size,
torch::Tensor& input_tokens, torch::Tensor& sampled_token_ids,
torch::Tensor& input_positions, torch::Tensor& seq_lens,
torch::Tensor& slot_mapping, torch::Tensor& block_tables,
torch::Tensor& paged_kv_indices, torch::Tensor& paged_kv_indptr,
torch::Tensor& paged_kv_last_page_len, torch::Tensor& block_table_bounds);
void cutlass_mla_decode(torch::Tensor const& out, torch::Tensor const& q_nope,
torch::Tensor const& q_pe,
torch::Tensor const& kv_c_and_k_pe_cache,