llama2.rs
burn
| llama2.rs | burn | |
|---|---|---|
| 3 | 34 | |
| 981 | 4,845 | |
| - | - | |
| 8.9 | 8.9 | |
| 6 months ago | 6 months ago | |
| Rust | Rust | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llama2.rs
-
Ask HN: Cheapest hardware to run Llama 2 70B
This code runs Llama2 quantized and unquantized in a roughly minimal way: https://github.com/srush/llama2.rs (though extracting the quantized 70B weights takes a lot of RAM). I'm running the 13B quantized model on ~10-11GB of CPU memory.
-
Candle: Torch Replacement in Rust
Nowhere near as neat as candle or ggml, but just released a 4-bit rust llama2 implementation with simd. Runs pretty fast.
https://github.com/srush/llama2.rs/
- Llama2.rs: One-file Rust implementation of Llama2
burn
-
Burn 0.10.0 Released 🔥 (Deep Learning Framework)
Release Note: https://github.com/burn-rs/burn/releases/tag/v0.10.0
- Deep Learning Framework in Rust: Burn 0.10.0 Released
-
Why Rust Is the Optimal Choice for Deep Learning, and How to Start Your Journey with the Burn Deep Learning Framework
The comprehensive, open-source deep learning framework in Rust, Burn, has recently undergone significant advancements in its latest release, highlighted by the addition of The Burn Book 🔥. There has never been a better moment to embark on your deep learning journey with Rust, as this book will guide you through your initial project, providing extensive explanations and links to relevant resources.
-
Candle: Torch Replacement in Rust
Burn (deep learning framework in rust) has WGPU backend (WebGPU) already. Check it out https://github.com/burn-rs/burn. It was released recently.
- Burn – A Flexible and Comprehensive Deep Learning Framework in Rust
-
Announcing Burn-Wgpu: New Deep Learning Cross-Platform GPU Backend
For more details about the latest release see the release notes: https://github.com/burn-rs/burn/releases/tag/v0.8.0.
-
Are there any ML crates that would compile to WASM?
Tract is the most well known ML crate in Rust, which I believe can compile to WASM - https://github.com/sonos/tract/. Burn may also be useful - https://github.com/burn-rs/burn.
-
Any working wgpu compute example that would run in a browser?
We, the burn team, are working on the wgpu backend (WebGPU) for Burn deep learning framework. You can check out the current state: https://github.com/burn-rs/burn/tree/main/burn-wgpu
-
I’ve fallen in love with rust so now what?
Here is the project: https://github.com/burn-rs/burn
-
Is anyone doing Machine Learning in Rust?
Disclaimer, I'm the main author of Burn https://burn-rs.github.io.
What are some alternatives?
burn - Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
candle - Minimalist ML framework for Rust
dfdx - Deep learning in Rust, with shape checked tensors and neural networks
euclid - Geometry primitives (basic linear algebra) for Rust
tch-rs - Rust bindings for the C++ api of PyTorch.
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
Graphite - 2D raster & vector editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow.
llama.cpp - LLM inference in C/C++
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference [Moved to: https://github.com/sonos/tract]
petals - 🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
L2 - l2 is a fast, Pytorch-style Tensor+Autograd library written in Rust