petrex

yt-dlp

A feature-rich command-line audio/video downloader

llama.cpp

LLM inference in C/C++

llama

Inference code for LLaMA models

DragGAN

Official Code for DragGAN (SIGGRAPH 2023)

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

barrier

Open-source KVM software

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

mojo

The Mojo Programming Language

mlc-llm

Universal LLM Deployment Engine with ML Compilation

stable-diffusion-webui-colab

stable diffusion webui colab

gpt-researcher

GPT based autonomous agent that does online comprehensive research on any given topic

web-llm

High-performance In-browser LLM Inference Engine

gorilla

Gorilla: An API store for LLMs

zfs

OpenZFS on Linux and FreeBSD

OpenChatKit

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

archinstall

Arch Linux installer - guided, templates etc.

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ

YoutubeDL-Material

Self-hosted YouTube downloader built on Material Design

NonSteamLaunchers-On-Steam-Deck

Installs the latest GE-Proton and Installs Non Steam Launchers under 1 Proton prefix folder and adds them to your steam library. Installs... Battle.net, Epic Games, Ubisoft, GOG, EA App, Amazon Games, itch.io , Legacy Games, The Humble Games Collection, IndieGala, Rockstar Games Launcher,PS Plus, Glyph, VKPlay & HoYoPlay. SD Card Support and Games.

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

llm-vscode

LLM powered development for VSCode

LLM-Reading-List

LLM papers I'm reading, mostly on inference and model compression

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

composable_kernel

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

so-vits-svc-4.0

SoftVC VITS Singing Voice Conversion

cutlass_fpA_intB_gemm

A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer