aboutsummaryrefslogtreecommitdiff
path: root/app/docs/backend-sglomni.md
AgeCommit message (Collapse)Author
4 daysrewrite backend documentationhistoria
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
5 daysfix: warn before using a likely too-big chunk size for sglang-omni modelshistoria
5 daysfeat: reserve 20% vram when running higgs with sglang-omnihistoria
6 daysfeat: sglang-omni model picker on manual server launchhistoria
6 daysfix: ZONOS2 only generating 1024 tokens maxhistoria
6 daysfeat: sglang backend supporthistoria