Commit History
Update recommended configurations
f248b35
badayvedat
commited on
Remove model preloading
5df3ede
badayvedat
commited on
Load 13B model with 8-bit/4-bit quantization to support more hardwares (#2)
c6dfdac
fix: start worker proc
255cd6e
badayvedat
commited on
docs: add notifier for gpu only inference
0b8daad
badayvedat
commited on
feat: Add LLaVA model
a824a18
badayvedat
commited on