feat(server): idle model auto-unload + pre-load memory guard (cross-platform CI) - #1

Closed

gqf2008 wants to merge 5 commits into

mainfrom

feat/server-memory-guard

Commits on Aug 25, 2026

feat(server): add --idle-unload-ms to auto-unload idle models
gqf2008
committed
1f70f9a
feat(server): refuse model load when host/GPU memory is insufficient
gqf2008
committed
454f099
fix(server): address code review for idle unload and memory guard
gqf2008
committed
d345331
ci(server): add cross-platform build+test matrix for memory guard
gqf2008
committed
5a0c1c4
ci(server): fix macOS build step to not run the nproc variant
gqf2008
committed
8d9d677