jackyYang6 a29ee57e15 [Feature] Support ThinkingBudget Logits processor to control thinking content length (#6367) ...

* 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>

2026-02-25 14:17:09 +08:00

..

ernie4_5_vl_processor

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00

paddleocr_vl_processor

[Models] Add Qwen3-VL Model Support (#5763)

2025-12-29 17:39:33 +08:00

qwen3_vl_processor

[Models] Add Qwen3-VL Moe Model Support (#5913)

2026-01-08 11:36:42 +08:00

qwen_vl_processor

[Models] Qwen3VL and Qwen3VL-Moe CUDA graph Support (#5962)

2026-01-09 17:09:02 +08:00

v1

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

2026-02-25 14:17:09 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

ernie4_5_processor.py

fix paddleformers fallback (#6465)

2026-02-23 15:29:13 +08:00

ernie4_5_tokenizer.py

delete ernie4_5_vl_tokenizer (#3631)

2025-08-27 20:36:02 +08:00

mm_data_processor.py

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00

preprocess.py

[Optimization] The pre- and post-processing pipeline do not perform dict conversion (#5494)

2026-01-22 00:50:52 +08:00

text_processor.py

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

2026-02-25 14:17:09 +08:00

tokenzier_client.py

[BugFix] fix decode time sleep bug (#5461)

2025-12-10 15:48:48 +08:00

utils.py

[Feature] consider multimodal model when dummy run (#6045)

2026-02-09 17:49:55 +08:00