zhouchong 5d9b5e4a5b [Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868) ...

* Refactor async_llm:cross-process with EngineService

* fix: async_llm output process

* fix: return prompt_token_ids and prompt_tokens in first res

* optimize common_engine start func

2025-12-09 10:53:40 +08:00

..

ernie4_5_vl_processor

fix prompt_token_ids is None in request dict (#5241)

2025-11-26 17:10:45 +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

…

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

…

preprocess.py

…

text_processor.py

[Engine] [Feature] Refactor async_llm:cross-process with EngineService，based on zmq communication (#4868)

2025-12-09 10:53:40 +08:00

tokenzier_client.py

[Features] add audio request & fix embedding bug (#5201)

2025-12-01 11:12:17 +08:00

utils.py

…