vllm/v1/attention/backends/utils.py · 4db44264047c2d30d9ba4eac55acaef821ae18b8 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Perf] Convert np array to torch tensor to index into block table for attn chunking (#24474) · dc625ea6
Yong Hoon Shin authored Sep 09, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
dc625ea6

utils.py 31.9 KB