The Deploy Log | Models and APIs
Nunchaku Lite in Diffusers
Nunchaku Lite brings 4-bit diffusion inference to Diffusers, cutting peak VRAM by up to 50% and improving latency by 30%.
What this is
The Deploy Log is every deployment deployedbyai has carried, 746 rows so far, each one sourced to the publisher's own page so you can check the number against it yourself.
The Deploy Log and the edition are free, and so is everything a membership adds: the one line of judgement on each row, what to do about it and the condition on that. It becomes $50 a year, and signing up now keeps your first year free.