This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
0d2689e0dfd5e9f74f361cab7701df0feee33ef3
vLLM
/
vllm
/
entrypoints
/
openai
/
completion
T
History
Chester
c599b5971f
[Bugfix][Frontend] Return all logprobs when completions requests logprobs=-1 (
#55717
)
...
Signed-off-by: Chester <
42577861+superdiaodiao@users.noreply.github.com
>
2026-10-12 17:05:55 +00:00
..
__init__.py
[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (
#32369
)
2026-01-15 07:41:34 +00:00
api_router.py
[Frontend][last/N] Move all non-OpenAI content out of the OpenAI folder. (
#56369
)
2026-09-11 05:33:26 +00:00
protocol.py
[Bugfix][Frontend] Reject beam search with echo and logprobs in /v1/completions (
#60876
)
2026-10-09 18:06:26 +00:00
serving.py
[Bugfix][Frontend] Return all logprobs when completions requests logprobs=-1 (
#55717
)
2026-10-12 17:05:55 +00:00