coreylowman / llama-dfdxLinks
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
Sorting:
- Low rank adaptation (LoRA) for Candle.☆147Updated last month
- Asynchronous CUDA for Rust.☆33Updated 7 months ago
- Llama2 LLM ported to Rust burn☆278Updated last year
- ☆23Updated last month
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆80Updated last year
- ☆86Updated 4 months ago
- Inference Llama 2 in one file of pure Rust 🦀☆233Updated last year
- A collection of optimisers for use with candle☆36Updated 2 weeks ago
- Example of tch-rs on M1☆53Updated last year
- A minimal OpenCL, CUDA, Vulkan and host CPU array manipulation engine / framework.☆73Updated last week
- A diffusers API in Burn (Rust)☆19Updated 10 months ago
- ☆30Updated 6 months ago
- Safe, portable, high performance compute (GPGPU) kernels.☆229Updated last year
- Andrej Karpathy's Let's build GPT: from scratch video & notebook implemented in Rust + candle☆71Updated last year
- Implementation of the Coursera ML course in Rust☆38Updated 3 months ago
- An extension library to Candle that provides PyTorch functions not currently available in Candle☆39Updated last year
- Unofficial Rust bindings to Apple's mlx framework☆159Updated this week
- Experimental compiler for deep learning models☆67Updated 2 weeks ago
- ☆58Updated 2 years ago
- Rust wrapper for Microsoft's ONNX Runtime (version 1.8)☆296Updated last year
- Tutorial for Porting PyTorch Transformer Models to Candle (Rust)☆296Updated 10 months ago
- DLPack safe Rust binding☆14Updated 2 years ago
- allms: One Rust Library to rule them aLLMs☆81Updated this week
- RAI: Rust ML framework with composable transformations like JAX.☆89Updated 10 months ago
- Flexible, reusable reinforcement learning (Q learning) implementation in Rust☆152Updated 11 months ago
- A Discord bot, written in Rust, that generates responses using the LLaMA language model.☆93Updated last year
- 8-bit floating point types for Rust☆45Updated 2 months ago
- Provides an interface layer to convert between n-dimensional types in different Rust crates☆54Updated 9 months ago
- Models and examples built with Burn☆244Updated last month
- ☆66Updated last year