KGrewal1 / candle-optimisersLinks
A collection of optimisers for use with candle
☆39Updated last week
Alternatives and similar repositories for candle-optimisers
Users that are interested in candle-optimisers are comparing it to the libraries listed below
Sorting:
- Low rank adaptation (LoRA) for Candle.☆153Updated 4 months ago
- An extension library to Candle that provides PyTorch functions not currently available in Candle☆40Updated last year
- A Keras like abstraction layer on top of the Rust ML framework candle☆23Updated last year
- GPU based FFT written in Rust and CubeCL☆23Updated 2 months ago
- ☆20Updated 10 months ago
- ☆33Updated 9 months ago
- implement llava using candle☆15Updated last year
- ☆24Updated 4 months ago
- Sample Python extension using Rust/PyO3/tch to interact with PyTorch☆37Updated last year
- Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package☆219Updated 2 months ago
- CLI utility to inspect and explore .safetensors and .gguf files☆26Updated 3 weeks ago
- Read and write tensorboard data using Rust☆21Updated last year
- LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!☆108Updated 2 years ago
- ☆90Updated 7 months ago
- 8-bit floating point types for Rust☆56Updated last week
- A single-binary, GPU-accelerated LLM server (HTTP and WebSocket API) written in Rust☆80Updated last year
- Experimental compiler for deep learning models☆68Updated 3 months ago
- Inference Llama 2 in one file of zero-dependency, zero-unsafe Rust☆38Updated 2 years ago
- Fast, Lightweight, Unified Engine for Text2Image Diffusion Models☆20Updated 4 months ago
- Blazingly fast inference of diffusion models.☆113Updated 4 months ago
- ☆58Updated 2 years ago
- A Deep Learning and preprocessing framework in Rust with support for CPU and GPU.☆132Updated last year
- Inference Llama 2 in one file of pure Rust 🦀☆233Updated last year
- Tutorial for Porting PyTorch Transformer Models to Candle (Rust)☆311Updated last year
- ☆130Updated last year
- A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Face☆37Updated last year
- Democratizing large model inference and training on any device.☆124Updated last week
- Transformers provides a simple, intuitive interface for Rust developers who want to work with Large Language Models locally, powered by t…☆18Updated last month
- Cookbook to build Rust Candle models☆81Updated last year
- ☆27Updated 2 years ago