KerfuffleV2 / smolrsrwkvLinks
A relatively basic implementation of RWKV in Rust written by someone with very little math and ML knowledge. Supports 32, 8 and 4 bit evaluation. It can also directly load PyTorch RWKV models.
☆93Updated last year
Alternatives and similar repositories for smolrsrwkv
Users that are interested in smolrsrwkv are comparing it to the libraries listed below
Sorting:
- ☆32Updated 2 years ago
- ☆58Updated 2 years ago
- tinygrad port of the RWKV large language model.☆45Updated 4 months ago
- GGML bindings that aim to be idiomatic Rust rather than directly corresponding to the C/C++ interface☆19Updated last year
- Rust+OpenCL+AVX2 implementation of LLaMA inference code☆549Updated last year
- Bleeding edge low level Rust binding for GGML☆16Updated last year
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆38Updated 2 years ago
- ☆27Updated last year
- Inference Llama 2 in one file of pure Rust 🦀☆233Updated last year
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆80Updated last year
- ☆20Updated 9 months ago
- Inference of Mamba models in pure C☆189Updated last year
- High-level, optionally asynchronous Rust bindings to llama.cpp☆226Updated last year
- Implementation of the RWKV language model in pure WebGPU/Rust.☆314Updated 3 weeks ago
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆313Updated last year
- LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!☆108Updated 2 years ago
- WebGPU LLM inference tuned by hand☆151Updated 2 years ago
- Implementing the BitNet model in Rust☆38Updated last year
- Unofficial python bindings for the rust llm library. 🐍❤️🦀☆75Updated last year
- Low rank adaptation (LoRA) for Candle.☆152Updated 3 months ago
- A collection of optimisers for use with candle☆37Updated last week
- Framework agnostic python runtime for RWKV models☆146Updated last year
- A highly customizable, full scale web backend for web-rwkv, built on axum with websocket protocol.☆26Updated last year
- LLaMA from First Principles☆51Updated 2 years ago
- A diffusers API in Burn (Rust)☆21Updated last year
- A Fish Speech implementation in Rust, with Candle.rs☆94Updated 2 months ago
- Port of Andrej Karpathy's minbpe to Rust☆25Updated last year
- RWKV models and examples powered by candle.☆18Updated 5 months ago
- ☆130Updated last year
- A collection of LLM token samplers in Rust☆18Updated last year