"vllm/vscode:/vscode.git/clone" did not exist on "281ca6c196a350cb4c9a9a430d23456764dd31cf"
-
Cody Yu authored
The 2nd PR for #4532. This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
a3a73ab0