A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.

LLM101n: Let's build a Storyteller

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

Puzzles for learning Triton

A massively parallel, high-level programming language

Language model alignment-focused deep learning curriculum

Tegon is an open-source, AI-first alternative to Jira, Linear

CUDA Templates for Linear Algebra Subroutines

Open weights language model from Google DeepMind, based on Griffin.

Minimalistic large language model 3D-parallelism training

A list of articles outside of the official MLIR docs that I've found useful for learning MLIR

MLIR For Beginners tutorial

C++ Insights - See your source code with the eyes of a compiler

Schedule-Free Optimization in PyTorch

Development repository for the Triton language and compiler

MLX: An array framework for Apple silicon

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

A high performance Python graph library implemented in Rust.

SGLang is yet another fast serving framework for large language models and vision language models.

Go ahead and axolotl questions

Fast bare-bones BPE for modern tokenizer training

BLAS-like Library Instantiation Software Framework

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

This is an online course where you can learn and master the skill of low-level performance analysis and tuning.

AgentSearch is a framework for powering search agents and enabling customizable local search.

evolve llm training instruction, from english instruction to any language.