This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
6ec0d8dbe4ccff35d042fafa29f2c141e553e7ae
vLLM
/
vllm
/
v1
/
sample
T
History
realliujiaxu
d2c919dcc2
[bugfix] fix bug when top_logprobs=0 with spec decoding (
#30059
)
...
Signed-off-by: realliujiaxu <
realliujiaxu@163.com
>
2025-12-12 09:03:35 -08:00
..
logits_processor
[Perf] Avoid pageable HtoD transfer in MinTokensLogitsProcessor (
#29826
)
2025-12-02 21:25:52 +00:00
ops
Guard FlashInfer sampler using the same check as FlashInfer attention backend (
#29415
)
2025-11-28 08:34:48 -08:00
tpu
[Doc]: fixing typos in diverse files (
#29492
)
2025-11-27 07:15:50 -08:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
metadata.py
Update
Optional[x]
->
x | None
and
Union[x, y]
to
x | y
(
#26633
)
2025-10-12 09:51:31 -07:00
rejection_sampler.py
[bugfix] fix bug when top_logprobs=0 with spec decoding (
#30059
)
2025-12-12 09:03:35 -08:00
sampler.py
[BugFix] Fix returned logprobs with spec decode + prefill chunking (
#29216
)
2025-11-22 22:41:25 +08:00