vllm/worker/model_runner.py · b7ee940a828de9d339345e28eee8b13d60d97f26 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[torch.compile] Hide KV cache behind torch.compile boundary (#11677) · cf5f000d
Chen Zhang authored Jan 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
cf5f000d

model_runner.py 87.5 KB