Run the big model on the workstation, with admission control and the 1.7B as the floor #96

Merged
kami merged 3 commits from task/489-workstation-deploy-mavgpud-on-workpc-and into master 2026-08-03 10:12:14 +02:00
Showing only changes of commit eca41798bd - Show all commits
+1
View File
@@ -15,6 +15,7 @@
"--batch-size", "2048",
"--ubatch-size", "512",
"--jinja",
"--chat-template-kwargs", "{\"enable_thinking\":false}",
"--spec-type", "draft-mtp",
"--spec-draft-n-max", "2"
],