vllm/v1/sample/ops/topk_topp_sampler.py · 32ef4983cd029d613172dbcf1edf91e62920bbc8 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[V1] Temporarily disable FlashInfer Rejection Sampler (#14788) · 32ef4983
Woosuk Kwon authored Mar 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
32ef4983

topk_topp_sampler.py 7.4 KB