Li, Jiang 3bbb4936dc [Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend and update documentation (#6125)

2024-07-26 13:50:10 -07:00

..

output_processor

Pipeline Parallel: Guard for KeyErrors at request abort (#6587)

2024-07-19 19:18:19 -07:00

__init__.py

Change the name to vLLM (#150)

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

arg_utils.py

[bitsandbytes]: support read bnb pre-quantized model (#5753)

2024-07-23 23:45:09 +00:00

async_llm_engine.py

[Hardware] [Intel] Enable Multiprocessing and tensor parallel in CPU backend and update documentation (#6125)

2024-07-26 13:50:10 -07:00

async_timeout.py

[Bugfix] AsyncLLMEngine hangs with asyncio.run (#5654)

2024-06-19 13:57:12 -07:00

llm_engine.py

[Bugfix] Miscalculated latency lead to time_to_first_token_seconds inaccurate. (#6686)

2024-07-24 08:58:42 -07:00

metrics.py

[Bugfix] StatLoggers: cache spec decode metrics when they get collected. (#6645)

2024-07-23 23:05:05 +00:00