vllm/v1/worker/gpu_model_runner.py · fe15729a2b77d760fcf99da76f15806c5eab33df · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[V1] Use custom ops for piecewise CUDA graphs (#10227) · fe15729a
Woosuk Kwon authored Nov 11, 2024
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
fe15729a

gpu_model_runner.py 31 KB