mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
Eric BuehlerandGitHub
efbe4a69fc
* Sketch the diffusion pipeline, loader, model, and FLUX model * Connect response part to openai server * Sketch the flux loader * Handle 256 limitiation of timestep distilliation model * Work on loading * Handle raw prompts for image gen models * Should build now * Clippy * Add diffusion plain model * Typos * Sketch a server example * Add parse_diffusion_arch * Add debug bound * Use as_any * Some fixes * Fix config * Loads now * Avoid empty prompt err * Fix overflow * Fix overflow * Use the correct processor * Add debugs * Cast to correct dtype * Squeeze * Use sharded and downcast repo * Better loading * Dont modify cache * Fix response * Use big t5 for now * Only load relevant tensors * Clamp for f16 * Do some things * Use sharded and downcast repo * Diffusion model case * Oops * Oops * Hotload t5xxl * Use only encoder parts * Don't cast it * Fix files * Format * Cast every layer * Updated resolution and prompt * Fix issue with dual running * Reduce lifetime of hotloaded t5 xxl * Offloading t5 layers to cpu * Add offloading config * Add Python, Rust support, docs * Add configurable height and width
274 B
274 B
Image generation model support in mistral.rs
Mistral.rs supports various modalities of models, including image generation models. Image generation models take text as input and generate images.
Please see docs for the following model types:
- FLUX.1 FLUX.md