vllm/engine/arg_utils.py · ad510309ee10e5182b99ee94ddc5ace716c65050 · OpenDAS / vllm_cscc · GitLab

"vllm/vscode:/vscode.git/clone" did not exist on "0ea30aa0007402dc983be3daf0df55bb546645a7"

Find file Blame History Permalink

Override attention metadata for fast prefill in some KV sharing setups (#21590) · ad510309
Yong Hoon Shin authored Jul 30, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
ad510309

arg_utils.py 79.7 KB