vllm/model_executor/layers/rotary_embedding.py · 7e1d5e5308fa3549dfed1821188d588260a03c8a · kecinstone / 2024pra-vllm · GitLab

"vllm/model_executor/layers/attention.py" did not exist on "a96d63c21d18ad6610adfcabd3aae02c6357334e"

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

rotary_embedding.py 14.2 KB