Sungjae Lee's starred repositories

KoMT-Bench

Official repository for KoMT-Bench built by LG AI Research

Language:PythonLicense:LGPL-3.0Stargazers:44Issues:0Issues:0

nebula

A scalable overlay networking tool with a focus on performance, simplicity and security

Language:GoLicense:MITStargazers:14212Issues:0Issues:0

vllm

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

Language:PythonLicense:Apache-2.0Stargazers:24994Issues:0Issues:0

LLM101n

LLM101n: Let's build a Storyteller

Stargazers:27061Issues:0Issues:0

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Language:PythonLicense:NOASSERTIONStargazers:2060Issues:0Issues:0

P-tuning-v2

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

Language:PythonLicense:Apache-2.0Stargazers:1952Issues:0Issues:0

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

Language:PythonLicense:NOASSERTIONStargazers:8223Issues:0Issues:0

NeMo-Aligner

Scalable toolkit for efficient model alignment

Language:PythonLicense:Apache-2.0Stargazers:479Issues:0Issues:0

flash-attention

Fast and memory-efficient exact attention

Language:PythonLicense:BSD-3-ClauseStargazers:12992Issues:0Issues:0

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Language:PythonLicense:NOASSERTIONStargazers:81436Issues:0Issues:0

trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

Language:PythonLicense:Apache-2.0Stargazers:1452Issues:0Issues:0

nvcc4jupyter

A plugin for Jupyter Notebook to run CUDA C/C++ code

Language:Jupyter NotebookLicense:MITStargazers:183Issues:0Issues:0

nvbandwidth

A tool for bandwidth measurements on NVIDIA GPUs.

Language:C++License:Apache-2.0Stargazers:261Issues:0Issues:0

corenet

CoreNet: A library for training deep neural networks

Language:PythonLicense:NOASSERTIONStargazers:6881Issues:0Issues:0

GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1985Issues:0Issues:0

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Language:PythonLicense:Apache-2.0Stargazers:2091Issues:0Issues:0

ZLUDA

CUDA on ??? GPUs

Language:RustLicense:Apache-2.0Stargazers:8807Issues:0Issues:0

ChatRTX

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

Language:TypeScriptLicense:NOASSERTIONStargazers:2619Issues:0Issues:0

StableCascade

Official Code for Stable Cascade

Language:Jupyter NotebookLicense:MITStargazers:6494Issues:0Issues:0

msccl

Microsoft Collective Communication Library

Language:C++License:NOASSERTIONStargazers:290Issues:0Issues:0

nccl

Optimized primitives for collective multi-GPU communication

Language:C++License:NOASSERTIONStargazers:3067Issues:0Issues:0

hfcxx

Hartree-Fock C++ code

Language:C++License:GPL-3.0Stargazers:28Issues:0Issues:0

Efficient-LLMs-Survey

[TMLR 2024] Efficient Large Language Models: A Survey

Stargazers:907Issues:0Issues:0

ml-engineering

Machine Learning Engineering Open Book

Language:PythonLicense:CC-BY-SA-4.0Stargazers:10480Issues:0Issues:0

juga

Juga is a stock price data fetcher

Language:PythonLicense:MITStargazers:5Issues:0Issues:0

dftcxx

C++ based DFT program for educational purposes

Language:C++License:GPL-3.0Stargazers:53Issues:0Issues:0

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.

Language:C++License:Apache-2.0Stargazers:7942Issues:0Issues:0

mlx

MLX: An array framework for Apple silicon

Language:C++License:MITStargazers:16200Issues:0Issues:0

deepmd-kit

A deep learning package for many-body potential energy representation and molecular dynamics

Language:C++License:LGPL-3.0Stargazers:1429Issues:0Issues:0

deepchem

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Language:PythonLicense:MITStargazers:5351Issues:0Issues:0