youkaichao b031a455a9

[torch.compile] add logging for compilation time (#10941) ...

Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2024-12-06 10:07:15 +00:00

..

multiprocessing

[LoRA] Change lora_tokenizers capacity (#10796)

2024-12-04 17:40:16 +00:00

output_processor

[Doc] Create a new "Usage" section (#10827)

2024-12-05 11:19:35 +08:00

__init__.py

Change the name to vLLM (#150)

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

arg_utils.py

[Doc] Create a new "Usage" section (#10827)

2024-12-05 11:19:35 +08:00

async_llm_engine.py

[Core][Performance] Add XGrammar support for guided decoding and set it as default (#10785)

2024-12-03 15:17:00 +08:00

async_timeout.py

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

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

llm_engine.py

[torch.compile] add logging for compilation time (#10941)

2024-12-06 10:07:15 +00:00

metrics_types.py

[Metrics] add more metrics (#4464)

2024-11-12 00:17:38 +08:00

metrics.py

[Frontend] correctly record prefill and decode time metrics (#10853)

2024-12-03 19:13:31 +00:00

protocol.py

[Misc] Rename embedding classes to pooling (#10801)

2024-12-01 14:36:51 +08:00