yangjianfengo1 af715db763 [Scheduler] Support chunk prefill for video input (#5107) ...

* add video chunk prefill

* add vit_merge=True for test_tokenizer_client.py

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>

2025-11-20 16:29:13 +08:00

..

ernie4_5_vl_processor

[BugFix] rollback max_tokens and min_tokens when continue to infer (#5082)

2025-11-19 18:43:42 +08:00

paddleocr_vl_processor

Update Unit Test for PaddleOCR-VL (#4802)

2025-11-04 22:40:15 +08:00

qwen_vl_processor

[BugFix] Fix ernie4_5_vl_processor.py and qwen_vl_processor.py can not disable thinking (#4762)

2025-11-04 16:00:32 +08:00

__init__.py

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

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

ernie4_5_processor.py

[BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686)

2025-10-30 19:45:41 +08:00

ernie4_5_tokenizer.py

delete ernie4_5_vl_tokenizer (#3631)

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

preprocess.py

[Feature] mm support prefix cache (#4134)

2025-10-27 17:39:51 +08:00

text_processor.py

[TSP] Support qwen3 moe tsp + cudagraph (#4871)

2025-11-10 23:37:51 +08:00

tokenzier_client.py

[Scheduler] Support chunk prefill for video input (#5107)

2025-11-20 16:29:13 +08:00

utils.py

rename ernie_xxx to ernie4_5_xxx (#3621)

2025-08-26 19:29:27 +08:00