local-inference / server.py

Commit History

Optimize build: lazy model loading + CPU torch wheel
b9ed0c9

ButterM40 commited on

Add per-token alternatives + hover tooltip UI
5a6a589

ButterM40 commited on

Add accelerate dependency and optimize model loading for memory constraints
b781094

ButterM40 commited on

Add accelerate dependency and optimize model loading for memory constraints
c75f720

ButterM40 commited on

Final_Working
84fc33b

Diego Adame commited on

Changes for Render
47ef678

Diego Adame commited on

Complete Code
1eaa5ce

Diego Adame commited on