"vscode:/vscode.git/clone" did not exist on "2e240c69a9874743abc8b0b681e8c13d675beda3"
-
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
The 2nd PR for #4532. This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).