test/srt/test_vlm_accuracy.py · e97e57e699e57de2104da791cb12406b332cd45e · change / sglang · GitLab

Find file Blame History Permalink

vlm: enable radix cache for qwen-vl models (#5349) · c998d04b
Mick authored Apr 24, 2025
```
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
```
c998d04b

test_vlm_accuracy.py 7.87 KB