vllm/worker/model_runner.py · 69d5ae38dc0dbc0b9074a344b4eb878c74c8c755 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[core][model] yet another cpu offload implementation (#6496) · 1c27d25f
youkaichao authored Jul 17, 2024
```
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
1c27d25f

model_runner.py 61.8 KB