YuehChuan

cudaMaster

notes for CUDA

screenshot-to-code

Drop in a screenshot and convert it to clean HTML/Tailwind/JS code

AIOS

AIOS: LLM Agent Operating System

bitsandbytes-windows

windows 11 CUDA12.2 8-bit CUDA functions for PyTorch for

ChatTTS

ChatTTS is a generative speech model for daily dialogue.

draw-a-ui

Draw a mockup and generate html for it

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

FineTuneViT

Finetune your ViT model

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

generative-ai-for-beginners

12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

graphcast

llama_walkthrough

Llama2 transformer walkthrough with code examples

llamafile

Distribute and run LLMs with a single file.

llm-baselines

llm-course

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

llm-viz

3D Visualization of an GPT-style LLM

llm.c

LLM training in simple, raw C/CUDA

mamba

mamba.py

A Mamba with parallel scan in PyTorch.

megablocks-public

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

nvbench

CUDA Kernel Benchmarking Library

Open-Sora

Building your own video generation model like OpenAI's Sora

prompt-lookup-decoding

safetensors-cpp

Header-only safetensors loader and saver in C++

SWE-agent

SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models

tapnet

Tracking Any Point (TAP)

unsloth

Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory

vit.cpp

Inference Vision Transformer (ViT) in plain C/C++ with ggml

xdp-tutorial

XDP tutorial