benchmarks/kernels/benchmark_paged_attention.py · 7e1d5e5308fa3549dfed1821188d588260a03c8a · OpenDAS / vllm_cscc · GitLab

"vllm/vscode:/vscode.git/clone" did not exist on "3b45075206f4847fdfb38d9a9139abad5fed8e31"

Find file Blame History Permalink

Remove hardcoded `device="cuda" ` to support more devices (#2503) · 96b6f475
Kunshang Ji authored Feb 02, 2024
```
Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
96b6f475

benchmark_paged_attention.py 6.94 KB