vllm/vllm
2024-03-29 23:26:44 +00:00
..
attention [ROCm][Bugfix] Fixed several bugs related to rccl path and attention selector logic (#3699) 2024-03-29 14:52:36 -07:00
core fix logging msg for block manager (#3701) 2024-03-28 23:29:55 +00:00
engine [BugFix] Fix tokenizer out of vocab size (#3685) 2024-03-29 08:18:59 -07:00
entrypoints [BugFix][Frontend] Fix completion logprobs=0 error (#3731) 2024-03-29 09:38:21 -07:00
executor [Core] Support multi-node inference(eager and cuda graph) (#3686) 2024-03-28 15:01:55 -07:00
lora [BugFix] Use consistent logger everywhere (#3738) 2024-03-29 23:26:44 +00:00
model_executor [BugFix] Use consistent logger everywhere (#3738) 2024-03-29 23:26:44 +00:00
spec_decode [CI] Try introducing isort. (#3495) 2024-03-25 07:59:47 -07:00
transformers_utils [BugFix] Fix tokenizer out of vocab size (#3685) 2024-03-29 08:18:59 -07:00
usage usage lib get version another way (#3735) 2024-03-29 15:57:08 -07:00
worker [Core][Test] move local_rank to the last arg with default value(#3711) 2024-03-28 21:19:45 -07:00
__init__.py bump version to v0.4.0 (#3712) 2024-03-29 12:28:33 -07:00
block.py Add Automatic Prefix Caching (#2762) 2024-03-02 00:50:01 -08:00
config.py [Bugfix] Command-R Max Model Length (#3727) 2024-03-29 12:27:51 -07:00
logger.py [CI] Try introducing isort. (#3495) 2024-03-25 07:59:47 -07:00
outputs.py [BugFix][Frontend] Fix completion logprobs=0 error (#3731) 2024-03-29 09:38:21 -07:00
py.typed Add py.typed so consumers of vLLM can get type checking (#1509) 2023-10-30 14:50:47 -07:00
sampling_params.py feat: implement the min_tokens sampling parameter (#3124) 2024-03-25 10:14:26 -07:00
sequence.py [2/N] Chunked prefill data update (#3538) 2024-03-28 10:06:01 -07:00
test_utils.py [Core][Test] move local_rank to the last arg with default value(#3711) 2024-03-28 21:19:45 -07:00
utils.py [Core][Bugfix]Refactor block manager for better testability (#3492) 2024-03-27 23:59:28 -07:00