xiaolei1013

MobileLLM

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

3D-model-datasets

Open-source 3D Model datasets

MeshCNN

Convolutional Neural Network for 3D meshes in PyTorch

TripoSR

llama_deploy

Deploy your agentic worfklows to production

OpenCLAY

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

harfbuzz

HarfBuzz text shaping engine

LLM101n

LLM101n: Let's build a Storyteller

curl

A command line tool and library for transferring data with URL syntax, supporting DICT, FILE, FTP, FTPS, GOPHER, GOPHERS, HTTP, HTTPS, IMAP, IMAPS, LDAP, LDAPS, MQTT, POP3, POP3S, RTMP, RTMPS, RTSP, SCP, SFTP, SMB, SMBS, SMTP, SMTPS, TELNET, TFTP, WS and WSS. libcurl offers a myriad of powerful features

unitycatalog

Open, Multi-modal Catalog for Data & AI

revideo

Create Videos with Code

YaFSDP

YaFSDP: Yet another Fully Sharded Data Parallel

zig

General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.

LLM-Game-Agents

This is a repo for studying the application of LLM Agents on Games

caddy

Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

ChatTTS

A generative speech model for daily dialogue.

zulip

Zulip server and web application. Open-source team chat that helps teams stay productive and focused.

open-webui

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

aframe

:a: Web framework for building virtual reality experiences.

unsloth

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

OpenFracture

Open source mesh slicing/fracturing utility for Unity

AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Tensor-Puzzles

Solve puzzles. Improve your pytorch.

minbpe

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

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

HVM

A massively parallel, optimal functional runtime in Rust

Bend

A massively parallel, high-level programming language

javascript-questions

A long list of (advanced) JavaScript questions, and their explanations :sparkles: