vllm/v1/worker/gpu_worker.py · 4f4713f96e01ebc799125a670c0bca9a2ae7d59d · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

[XPU] [torch.compile] Skipping CUDA graph memory estimation to avoid startup errors. (#39977) · 4f4713f9
Chaojun Zhang authored Apr 20, 2026
```
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
4f4713f9

gpu_worker.py 43.9 KB