3 people c6741b2ad4 [Model] Support Unlimited OCR (#46564) ...

Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>

2026-06-27 23:09:18 -07:00

..

__init__.py

[Bugfix] Fix RuntimeError: Already borrowed by adding thread-safe Hugging Face fast-tokenizer wrappers (#41181)

2026-05-05 14:04:01 +00:00

deepseek_v4_encoding.py

[Feat] DeepSeek V4 Rebased (#40860)

2026-04-26 18:31:08 -07:00

deepseek_v4.py

[DSV4] Support max reasoning effort (#40982)

2026-04-29 11:03:47 +00:00

deepseek_v32_encoding.py

…

deepseek_v32.py

[Bugfix] Fix DeepSeek-V3.2 tokenizer stripping spaces (#37004)

2026-03-13 22:55:36 +00:00

detokenizer_utils.py

…

fastokens.py

Deprecated 1st generation Qwen and QwenVL models (#45131)

2026-06-10 14:55:33 +00:00

hf.py

[Bugfix] Return the tokenizer from maybe_make_thread_pool so it survives pickling (#45460)

2026-06-13 06:01:35 +00:00

kimi_audio.py

Add vLLM library info to Hugging Face Hub requests (#43857)

2026-05-29 14:04:58 +00:00

mistral.py

Deprecate Transformers v4 support (#45161)

2026-06-11 11:04:01 +08:00

protocol.py

…

registry.py

[Model] Support Unlimited OCR (#46564)

2026-06-27 23:09:18 -07:00