vllm/v1/worker/gpu/model_runner.py · 62d54ba46db25b95de2d21e46f4b57b5502ed747 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[Model Runner V2] Optimize CUDA graph capture time (#29275) · 62d54ba4
Woosuk Kwon authored Nov 23, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
62d54ba4

model_runner.py 36.9 KB