Woosuk Kwon d7a4f2207b [V1] Do not use inductor for piecewise CUDA graphs (#10225) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2024-11-11 11:05:57 -08:00

..

attention

[V1] Make v1 more testable (#9888)

2024-11-06 11:57:35 -08:00

core

[V1] Prefix caching (take 2) (#9972)

2024-11-07 17:34:44 -08:00

engine

[V1] Allow tokenizer_mode and trust_remote_code for Detokenizer (#10211)

2024-11-11 18:01:18 +08:00

executor

[V1] Fix Configs (#9971)

2024-11-04 00:24:40 +00:00

sample

[V1] Support per-request seed (#9945)

2024-11-03 09:14:17 -08:00

tokenizer

[V1] Fix detokenizer ports (#10224)

2024-11-11 10:42:07 -08:00

worker

[V1] Do not use inductor for piecewise CUDA graphs (#10225)

2024-11-11 11:05:57 -08:00

outputs.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

request.py

[V1] Add all_token_ids attribute to Request (#10135)

2024-11-07 17:08:24 -08:00

utils.py

[V1] Add all_token_ids attribute to Request (#10135)

2024-11-07 17:08:24 -08:00