LLM training in simple, raw C/CUDA

Transformers with Arbitrarily Large Context

Enjoy the magic of Diffusion models!

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

FlashInfer: Kernel Library for LLM Serving

[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.

😎 Awesome Cloudflare Workers

Implementation for MatMul-free LM.

Smart pointers for the (GNU) C programming language

Extending the HDF5 library to support intelligent I/O buffering for deep memory and storage hierarchy systems

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

TerminalTextEffects (TTE) is a terminal visual effects engine, application, and Python library.

ldd as a tree

Powerful menu bar manager for macOS

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Hackable and optimized Transformers building blocks, supporting a composable construction.

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Generative AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. It features AI personas, AGI functions, multi-model chats, text-to-image, voice, response streaming, …

Curated list of useful LLM / Analytics / Datascience resources

LLM inference in C/C++

Tools for merging pretrained large language models.

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

Cybernetically enhanced web apps

A simple code for plotting figure, colorbar, and cropping with python

NCCL tests for ALCF machines