apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] fix speculate_limit_thinking_content_length (#5590)

Browse Source 
* fix speculate_limit_thinking_content_length

* update
This commit is contained in:
Yuanle Liu
2025-12-16 20:31:45 +08:00
committed by GitHub
parent 7140939c51
commit 867803ae10
5 changed files with 1 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -1029,7 +1029,6 @@ void SpeculateLimitThinkingContentLengthV1(
const paddle::Tensor& step_idx,
const paddle::Tensor& limit_think_status,
const paddle::Tensor& accept_num,
const paddle::Tensor& seq_lens_decoder,
const paddle::Tensor& stop_flags,
const paddle::Tensor& eos_token_ids,
const int64_t think_end_id);
@@ -1040,7 +1039,6 @@ void SpeculateLimitThinkingContentLengthV2(
const paddle::Tensor& step_idx,
const paddle::Tensor& limit_think_status,
const paddle::Tensor& accept_num,
const paddle::Tensor& seq_lens_decoder,
const paddle::Tensor& stop_flags,
const int64_t think_end_id,
const int64_t line_break_id);