vllm/v1/worker/gpu_ubatch_wrapper.py · bb79c4da2fc9a07935782a1f229c288055b815c4 · OpenDAS / vllm_cscc · GitLab

"vllm/vscode:/vscode.git/clone" did not exist on "e3b12667d46f74092d87777ffe9736e4baa116ae"

Find file Blame History Permalink

Reduce the Cuda Graph memory footprint when running with DBO (#25779) · bb79c4da
Sage Moore authored Sep 26, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
bb79c4da

gpu_ubatch_wrapper.py 16.9 KB