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.
☆94Updated 2 years ago
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
- GGML bindings that aim to be idiomatic Rust rather than directly corresponding to the C/C++ interface☆19Updated 2 years ago
- Bleeding edge low level Rust binding for GGML☆16Updated last year
- ☆58Updated 2 years ago
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆79Updated last year
- Rust+OpenCL+AVX2 implementation of LLaMA inference code☆548Updated last year
- ☆20Updated 11 months ago
- High-level, optionally asynchronous Rust bindings to llama.cpp☆230Updated last year
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆39Updated 2 years ago
- Inference Llama 2 in one file of pure Rust 🦀☆234Updated 2 years ago
- LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!☆109Updated 2 years ago
- Implementation of the RWKV language model in pure WebGPU/Rust.☆315Updated 3 weeks ago
- Low rank adaptation (LoRA) for Candle.☆162Updated 5 months ago
- Implementing the BitNet model in Rust☆39Updated last year
- Inference of Mamba models in pure C☆192Updated last year
- tinygrad port of the RWKV large language model.☆45Updated 6 months ago
- A collection of optimisers for use with candle☆40Updated last month
- WebGPU LLM inference tuned by hand☆151Updated 2 years ago
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆314Updated last year
- A diffusers API in Burn (Rust)☆21Updated last year
- ☆40Updated 2 years ago
- ☆27Updated 2 years ago
- LLaMA from First Principles☆51Updated 2 years ago
- An extension library to Candle that provides PyTorch functions not currently available in Candle☆39Updated last year
- ☆133Updated last year
- A highly customizable, full scale web backend for web-rwkv, built on axum with websocket protocol.☆26Updated last year
- Easy-to-use Rust bindings to the Whisper.cpp machine learning transcription library!☆23Updated last year
- RWKV models and examples powered by candle.☆19Updated 7 months ago
- Rust implementation of Huggingface transformers pipelines using onnxruntime backend with bindings to C# and C.☆39Updated 2 years ago
- Sample Python extension using Rust/PyO3/tch to interact with PyTorch☆38Updated last year