haimlust

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

kind

Temporary repository for Kind2's refactor based on HVM2

diffusion-forcing

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

arc-dsl

Domain Specific Language for the Abstraction and Reasoning Corpus

DiffSynth-Studio

Enjoy the magic of Diffusion models!

LLM101n

LLM101n: Let's build a Storyteller

iptv

Collection of publicly available IPTV channels from all over the world

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

alphageometry

path-to-senior-engineer-handbook

All the resources you need to get to Senior Engineer and beyond

quartz

🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites

InvokeAI

InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

phidata

Build AI Assistants with memory, knowledge and tools.

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

semantic-autocomplete

A blazing-fast semantic search React component. Match by meaning, not just by letters. Search as you type without waiting (no debounce needed). Rank by cosine similarity.

zero_to_gpt

Go from no deep learning knowledge to implementing GPT.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn to code for free.

supervision

We write your reusable computer vision tools. 💜

professional-programming

A collection of learning resources for curious software engineers

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

cs-video-courses

List of Computer Science courses with video lectures.

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

data-engineering-zoomcamp

Free Data Engineering course!

awesome-applied-ct

ACT community resources

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

resource-stream

CUDA related news and material links

os01

Bootstrap yourself to write an OS from scratch. A book for self-learner.