apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature][MTP]update multi-draft-token strategy (#3369)

Browse Source 
* update multi-draft-token strategy

* fix format

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
freeliuzc
2025-08-18 13:59:56 +08:00
committed by GitHub
parent 3ee6053e5d
commit a12d0bc549
4 changed files with 69 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -676,6 +676,7 @@ void DraftModelPreprocess(const paddle::Tensor& draft_tokens,
const paddle::Tensor& batch_drop,
const paddle::Tensor& accept_tokens,
const paddle::Tensor& accept_num,
const paddle::Tensor& base_model_seq_lens_this_time,
const paddle::Tensor& base_model_seq_lens_encoder,
const paddle::Tensor& base_model_seq_lens_decoder,
const paddle::Tensor& base_model_step_idx,