coreylowman / llama-dfdx
LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!
☆104Updated last year
Alternatives and similar repositories for llama-dfdx:
Users that are interested in llama-dfdx are comparing it to the libraries listed below
- Low rank adaptation (LoRA) for Candle.☆144Updated 7 months ago
- Example of tch-rs on M1☆53Updated last year
- ☆84Updated 2 months ago
- Asynchronous CUDA for Rust.☆31Updated 4 months ago
- Llama2 LLM ported to Rust burn☆277Updated 11 months ago
- ☆57Updated last year
- Andrej Karpathy's Let's build GPT: from scratch video & notebook implemented in Rust + candle☆72Updated 11 months ago
- An extension library to Candle that provides PyTorch functions not currently available in Candle☆38Updated last year
- A collection of optimisers for use with candle☆34Updated 4 months ago
- A minimal OpenCL, CUDA, Vulkan and host CPU array manipulation engine / framework.☆73Updated this week
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆79Updated last year
- Inference Llama 2 in one file of pure Rust 🦀☆233Updated last year
- Experimental compiler for deep learning models☆28Updated last month
- ☆28Updated 4 months ago
- ☆19Updated 5 months ago
- ☆21Updated 8 months ago
- Implementation of the Coursera ML course in Rust☆36Updated last month
- Models and examples built with Burn☆223Updated 3 weeks ago
- Asynchronous TensorRT for Rust.☆24Updated 4 months ago
- Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package☆190Updated 3 weeks ago
- Rust wrapper for Microsoft's ONNX Runtime (version 1.8)☆289Updated last year
- Fast serverless LLM inference, in Rust.☆65Updated 3 weeks ago
- ☆25Updated last year
- A neural network inference library, written in Rust.☆60Updated 8 months ago
- A diffusers API in Burn (Rust)☆19Updated 8 months ago
- ☆66Updated last year
- Simplistic API for deep learning tensor operations☆28Updated last month
- A fun, hackable, GPU-accelerated, neural network library in Rust, written by an idiot☆128Updated 9 months ago
- Safe, portable, high performance compute (GPGPU) kernels.☆223Updated 9 months ago
- 8-bit floating point types for Rust☆46Updated last week