This website requires JavaScript.
Explore
Help
Sign In
xinyun
/
vllm
Watch
1
Star
0
Fork
0
You've already forked vllm
mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced
2026-05-10 19:16:52 +08:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
vllm
/
vllm
/
v1
/
sample
History
Woosuk Kwon
41fb013d29
[V1][Spec Decode] Always use argmax for sampling draft tokens (
#16899
)
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-23 14:57:43 -07:00
..
ops
[V1][TPU] Enable Top K (
#15489
)
2025-04-17 18:18:11 +00:00
tpu
[TPU][V1] Enable Top-P (
#16843
)
2025-04-22 00:46:07 +00:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
metadata.py
[V1] Support bad_words in sampler (
#13376
)
2025-03-08 14:50:26 -08:00
rejection_sampler.py
[V1][Spec Decode] Always use argmax for sampling draft tokens (
#16899
)
2025-04-23 14:57:43 -07:00
sampler.py
[Bugfix] Validate logit biases to prevent out of vocab ids crashing engine (
#16529
)
2025-04-12 20:19:19 +00:00