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
021cdf72bc2295b5dcb60fcbc4b0dae66831cf77
vLLM
/
vllm
/
v1
/
sample
T
History
Jonathan Mamou
and
Li, Jiang <jiang1.li@intel.com>
351c72d6e5
[CPU] Skip Triton kernel monkey-patches when Triton-CPU is available (
#44991
)
...
Signed-off-by: jmamou <
jonathan.mamou@intel.com
> Co-authored-by: Li, Jiang <
jiang1.li@intel.com
>
2026-06-18 18:59:30 +08:00
..
logits_processor
[Reasoning] Support for speculative decoding with thinking budget (
#34668
)
2026-04-29 06:14:52 +00:00
ops
[ROCm][CI] Defer AITER sampler import and isolate server test PYTHONPATH (
#44823
)
2026-06-10 08:56:11 +00:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
metadata.py
[Reasoning] Support for speculative decoding with thinking budget (
#34668
)
2026-04-29 06:14:52 +00:00
rejection_sampler.py
[CPU] Skip Triton kernel monkey-patches when Triton-CPU is available (
#44991
)
2026-06-18 18:59:30 +08:00
sampler.py
[BUG] Fix FP64 Gumbel precision coverage (
#43150
)
2026-06-05 19:04:14 +08:00
thinking_budget_state.py
[CI] Reject out-of-vocabulary before they reach the GPU logprob path (
#44042
)
2026-06-02 22:27:52 -05:00