ktaebum

ktaebum's Stars

• sho-87/kanagawa-paper.nvim

  Remixed Kanagawa colourscheme with muted colors. For Neovim.

  Language:Lua542

• pytorch-labs/gpt-fast

  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

  Language:Python5.4k492

• hemingkx/SpeculativeDecodingPapers

  📰 Must-read papers and blogs on Speculative Decoding ⚡️

  28512

• friendliai/LLMServingPerfEvaluator

  Language:Python35

• mit-han-lab/qserve

  QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

  Language:Python36014

• xai-org/grok-1

  Grok open release

  Language:Python49.2k8.3k

• ColfaxResearch/cutlass-kernels

  Language:Cuda12024

• NVIDIA/cutlass

  CUDA Templates for Linear Algebra Subroutines

  Language:C++5k857

• projekt0n/github-nvim-theme

  GitHub's Neovim themes

  Language:Lua2k106

• AIoT-MLSys-Lab/Efficient-LLMs-Survey

  [TMLR 2024] Efficient Large Language Models: A Survey

  87873

• federico-busato/Modern-CPP-Programming

  Modern C++ Programming Course (C++03/11/14/17/20/23/26)

  Language:HTML11.5k771

• AlexvZyl/nordic.nvim

  🌒 Nord for Neovim, but warmer and darker. Supports a variety of plugins and other platforms.

  Language:Lua65839

• friendliai/friendli-client

  Friendli: the fastest serving engine for generative AI

  Language:Python377

• NVIDIA/TransformerEngine

  A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

  Language:Python1.7k274

• mosaicml/examples

  Fast and flexible reference benchmarks

  Language:Shell430122

• sharu725/online-cv

  A minimal Jekyll Theme to host your resume (CV) on GitHub with a few clicks.

  Language:CSS3.1k5.9k

• NVIDIA/apex

  A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

  Language:Python8.2k1.4k

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python12.7k1.1k

• huggingface/peft

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

  Language:Python15.3k1.5k

• microsoft/DeepSpeed

  DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

  Language:Python34.1k4k

• ml-energy/zeus

  Deep Learning Energy Measurement and Optimization

  Language:Python18425

• alibaba/EasyParallelLibrary

  Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.

  Language:Python25749

• cpburnz/python-pathspec

  Utility library for gitignore style pattern matching of file paths.

  Language:Python14541

• friendliai/FAI-Model

  FriendliAI Model Hub

  Language:Python872

• alpa-projects/alpa

  Training and serving large-scale neural networks with auto parallelization.

  Language:Python3k347

• friendliai/periflow-cli

  Welcome to PeriFlow CLI ☁︎

  Language:Python12

• rust-lang/rustlings

  :crab: Small exercises to get you used to reading and writing Rust code!

  Language:Rust51.7k9.9k

• inancgumus/learngo

  ❤️ 1000+ Hand-Crafted Go Examples, Exercises, and Quizzes. 🚀 Learn Go by fixing 1000+ tiny programs.

  Language:Go18.6k2.5k

• RustPython/RustPython

  A Python Interpreter written in Rust

  Language:Rust18.1k1.2k

• sxs-collaboration/spectre

  SpECTRE is a code for multi-scale, multi-physics problems in astrophysics and gravitational physics.

  Language:C++155188