Hacker News
- (Machine Learning) I spent 12+ hours trying to interface with Python/Pytorch/Tensorflow before learning about a new pure-Rust Tensor implementation from Hugging Face called "Candle". By comparison, it's been a joy to work with so far. https://github.com/huggingface/candle 14 comments rust
- [P] Candle: Torch Replacement in Rust https://github.com/huggingface/candle 9 comments machinelearning
Linking pages
- GitHub - rust-unofficial/awesome-rust: A curated list of Rust code and resources. https://github.com/rust-unofficial/awesome-rust 178 comments
- GitHub - evilsocket/cake: Distributed LLM inference for mobile, desktop and server. https://github.com/evilsocket/cake 20 comments
- GitHub - rust-unofficial/awesome-rust: A curated list of Rust code and resources. https://github.com/rust-unofficial/awesome-rust?tab=readme-ov-file#database 9 comments
- GitHub - evgenyigumnov/candle-simplified-example: A simplified example in Rust of training a neural network and then using it based on the Candle Framework by Hugging Face. https://github.com/evgenyigumnov/candle-simplified-example 6 comments
- GitHub - vincev/coze: An egui app for prompting a local offline LLM model. https://github.com/vincev/coze 4 comments
- GitHub - kaxap/candle-go: Use HuggingFace's Candle with Go. https://github.com/kaxap/candle-go 2 comments
- burn-rs https://burn.dev/blog/creating-high-performance-asynchronous-backends-with-burn-compute 2 comments
- GitHub - ShelbyJenkins/candle_embed: A simple, CUDA or CPU powered, library for creating vector embeddings using Candle and models from Hugging Face https://github.com/ShelbyJenkins/candle_embed 2 comments
- GitHub - huggingface/text-embeddings-inference: A blazing fast inference solution for text embeddings models https://github.com/huggingface/text-embeddings-inference 0 comments
- Carton now supports running ML models from C and C++ | Vivek Panyam https://blog.vivekpanyam.com/carton-now-supports-c-cpp 0 comments
- GitHub - tracel-ai/burn: Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals. https://github.com/Tracel-AI/burn 0 comments
- The GPU Poor strike back - by Omar Sanseviero https://thehackerllama.substack.com/p/the-gpu-poor-strike-back 0 comments
- GitHub - flawedmatrix/mamba-ssm: Implementation of mamba with rust https://github.com/flawedmatrix/mamba-ssm 0 comments
- GitHub - gmmyung/eerie: Rustic bindings to the IREE Compiler/Runtime https://github.com/gmmyung/eerie 0 comments
- GitHub - danielclough/fireside-chat: An LLM interface implemented in pure Rust using HuggingFace/Candle over Axum Websockets, an SQLite Database, and a Leptos (Wasm) frontend packaged with Tauri! https://github.com/danielclough/fireside-chat 0 comments
- GitHub - EricLBuehler/mistral.rs: Blazingly fast LLM inference. https://github.com/EricLBuehler/mistral.rs 0 comments
- GitHub - evilsocket/llama3-cake: Distributed LLama3 inference. https://github.com/evilsocket/llama3-cake 0 comments
Linked pages
- GitHub - ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++ https://github.com/ggerganov/llama.cpp 286 comments
- GitHub - karpathy/llama2.c: Inference Llama 2 in pure C, single file, fp32, haha https://github.com/karpathy/llama2.c 167 comments
- GitHub - huggingface/tokenizers: 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production https://github.com/huggingface/tokenizers 47 comments
- http://localhost:8081 8 comments
- What Is the Python GIL and Will They Get Rid of It? https://www.backblaze.com/blog/the-python-gil-past-present-and-future/ 3 comments
- GitHub - huggingface/safetensors: Simple, safe way to store and distribute tensors https://github.com/huggingface/safetensors 1 comment
- GitHub - coreylowman/dfdx: Deep learning in Rust, with shape checked tensors and neural networks https://github.com/coreylowman/dfdx 1 comment
- Candle Segment Anything Wasm - a Hugging Face Space by radames https://huggingface.co/spaces/radames/candle-segment-anything-wasm 1 comment
- GitHub - NVIDIA/cutlass: CUDA Templates for Linear Algebra Subroutines https://github.com/NVIDIA/cutlass 0 comments
- GitHub - burn-rs/burn: Burn - A Flexible and Comprehensive Deep Learning Framework in Rust https://github.com/burn-rs/burn 0 comments
- Candle Yolo - a Hugging Face Space by lmz https://huggingface.co/spaces/lmz/candle-yolo 0 comments
- Candle Llama2 - a Hugging Face Space by lmz https://huggingface.co/spaces/lmz/candle-llama2 0 comments
- https://github.com/floneum/floneum/tree/master/kalosm 0 comments
Related searches:
Search whole site: site:github.com
Search title: GitHub - huggingface/candle: Minimalist ML framework for Rust
See how to search.