Lists (7)
Stars
A curated list of resources for learning and exploring Triton, OpenAI's programming language for writing efficient GPU code.
Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
A modern runtime for JavaScript and TypeScript.
Generate instructions datasets for the fine-tuning purposes.
Simple, hackable and fast implementation for training/finetuning medium-sized LLaMA-based models
Development repository for the Triton language and compiler
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory
ChirpStack open-source LoRaWAN Network Server
Curated list of resources for Embedded and Low-level development in the Rust programming language
FeOs - A Framework for Equations of State and Classical Density Functional Theory
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
DSPy: The framework for programming—not prompting—language models
AdalFlow: The library to build & auto-optimize LLM applications.
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Quill is a modern WYSIWYG editor built for compatibility and extensibility
Lightning-fast and Powerful Code Editor written in Rust
Implementation of the RWKV language model in pure WebGPU/Rust.
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
Distribute and run LLMs with a single file.