vllm/sequence.py · e493e48524e9e78ab33eafec6461b3940e361189 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[V0][Bugfix] Fix parallel sampling performance regression when guided decoding is enabled (#17731) · e493e485
Madeesh Kannan authored May 23, 2025
```
Signed-off-by: Madeesh Kannan <shadeMe@users.noreply.github.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
```
e493e485

sequence.py 60.7 KB