biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V0 Deprecation] Remove advance_step (#22969)

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

19
csrc/torch_bindings.cpp
View File

@@ -142,25 +142,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
ops.def("gelu_quick(Tensor! out, Tensor input) -> ()");
ops.impl("gelu_quick", torch::kCUDA, &gelu_quick);
// prepare_inputs advance_step
ops.def(
"advance_step_flashattn(int num_seqs, int num_queries, int block_size, "
"Tensor! input_tokens, Tensor sampled_token_ids, "
"Tensor! input_positions, Tensor! seq_lens, Tensor! slot_mapping, "
"Tensor block_tables) -> ()");
ops.impl("advance_step_flashattn", torch::kCUDA, &advance_step_flashattn);
ops.def(
"advance_step_flashinfer("
" int num_seqs, int num_queries, int block_size,"
" Tensor! input_tokens, Tensor sampled_token_ids,"
" Tensor! input_positions, Tensor! seq_lens, Tensor! slot_mapping,"
" Tensor block_tables, Tensor! paged_kv_indices,"
" Tensor! paged_kv_indptr, Tensor! paged_kv_last_page_len,"
" Tensor! block_table_bounds"
") -> ()");
ops.impl("advance_step_flashinfer", torch::kCUDA, &advance_step_flashinfer);
// Layernorm
// Apply Root Mean Square (RMS) Normalization to the input tensor.
ops.def(