Pablo Guerrero Rosel's starred repositories
mistral.rs
Blazingly fast LLM inference.
candle-lora
Low rank adaptation (LoRA) for Candle.
stable-diffusion-burn
Stable Diffusion v1.4 ported to Rust's burn framework
llama2-burn
Llama2 LLM ported to Rust burn
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
diffusers-rs
An implementation of the diffusers api in Rust
translateLocally
Fast and secure translation on your local machine, powered by marian and Bergamot.
multiqueue2
A fast mpmc queue with broadcast capabilities. Known as multiqueue too.
vst_window
Cross-platform windowing library for VST plugins, written in Rust
flutter_rust_bridge
Flutter/Dart <-> Rust binding generator, feature-rich, but seamless and simple.
cargo-metadata
How to indicate WASM support in Rust crates?
webrtc-unreliable
Just enough hacks to get unreliable unordered WebRTC data channels between a browser and a server
jni-bindgen
Generate Rust JVM FFI wrappers around APIs defined by .jar or .class files, because maintaining your own hand-written bindings is an exercise in boredom, soundness bugs, and pain.