vllm/v1/worker/gpu_model_runner.py · fdea8ec16775e1645620b5ff46b799d60df4624c · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[V1] VLM - enable processor cache by default (#11305) · fdea8ec1
Alexander Matveev authored Dec 18, 2024
```
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
```
fdea8ec1

gpu_model_runner.py 32.8 KB