aboutsummaryrefslogtreecommitdiff
path: root/app/backends/sglomni/configs
AgeCommit message (Collapse)Author
5 daysfix: increase gpu memory for MOSS with gplang-omni to .87historia
5 daysfeat: gplang-omni reserves 70% of gpu 0 memory, preventing oom errors on ↵historia
consumer cards
6 daysfix: warn before using a likely too-big chunk size for sglang-omni modelshistoria
6 daysfeat: reserve 20% vram when running higgs with sglang-omnihistoria
6 daysfeat: sglang backend supporthistoria