vllm/model_executor/models/config.py · a403d0fa41cc68e3b6da4e1097dc896fde2f1a6a · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[V1] [Hybrid] Enable Full CUDA graph by default for hybrid models in V1 (#22594) · 5f1af97f
Thomas Parnell authored Aug 27, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
5f1af97f

config.py 16.1 KB