IlyasMoutawwakil

privateGPT

Interact with your documents using the power of GPT, 100% privately, no data leaks

uBlock

uBlock Origin - An efficient blocker for Chromium and Firefox. Fast and lean.

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

onnx

Open standard for machine learning interoperability

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

candle

Minimalist ML framework for Rust

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

text-generation-inference

Large Language Model Text Generation Inference

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

insanely-fast-whisper

GPU-Puzzles

Solve puzzles. Learn CUDA.

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course

AutoGPTQ

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

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

text-embeddings-inference

A blazing fast inference solution for text embeddings models

docquery

An easy way to extract information from documents

mteb

MTEB: Massive Text Embedding Benchmark

FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

llm-vscode

LLM powered development for VSCode

cuda-python

CUDA Python Low-level Bindings

attention_sinks

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

quanto

A pytorch Quantization Toolkit

OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

SpQR

hydra-moe

NEFTune

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

onnxscript

ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.

scrape-open-llm-leaderboard

Scrape and export data from the Open LLM Leaderboard.