apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature] Support ThinkingBudget Logits processor to control thinking content length (#6367)

Browse Source 
* feat: add thinking budget logits processor

* add unittest

* fix pre-commit

* add unittest

* docs: clarify operator-level vs logits processor usage and conflict guidance

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
jackyYang6
2026-02-25 14:17:09 +08:00
committed by GitHub
parent 1405d7d5d7
commit a29ee57e15
12 changed files with 1861 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/worker/worker_process.py
+1
View File
@@ -821,6 +821,7 @@ def parse_args():
help="chunk size of moe input",
)
parser.add_argument("--ori_vocab_size", type=int, default=None)
parser.add_argument("--think_start_id", type=int, default=-1)
parser.add_argument("--think_end_id", type=int, default=-1)
parser.add_argument("--image_patch_id", type=int, default=-1)
parser.add_argument("--line_break_id", type=int, default=-1)