Travis Johnson beb16b2c81 [Bugfix] Handle <|tool_call|> token in granite tool parser (#11039) ...

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

2024-12-10 10:27:11 +00:00

..

openai

[Bugfix] Handle <|tool_call|> token in granite tool parser (#11039)

2024-12-10 10:27:11 +00:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

api_server.py

bugfix: fix the bug that stream generate not work (#2756)

2024-11-09 10:09:48 +00:00

chat_utils.py

[Model]: Add support for Aria model (#10514)

2024-11-25 18:10:55 +00:00

launcher.py

[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (#8157)

2024-09-18 13:56:58 +00:00

llm.py

[Bugfix] Fix usage of deprecated decorator (#11025)

2024-12-10 13:45:47 +08:00

logger.py

[Frontend] API support for beam search (#9087)

2024-10-05 23:39:03 -07:00