wzzju

wzzju's Stars

• huggingface/nanotron

  Minimalistic large language model 3D-parallelism training

  Language:Python1.1k107

• huggingface/candle

  Minimalist ML framework for Rust

  Language:Rust15.3k897

• AIMPED/plotly_dash

  A collection of small dash apps which I created for learning purposes. Some of them answer questions asked on the plotly forum. https://community.plotly.com/

  Language:Python111

• liguodongiot/llm-action

  本项目旨在分享大模型相关技术原理以及实战经验。

  Language:HTML9.4k916

• mli/paper-reading

  深度学习经典、新论文逐段精读

  26.5k2.4k

• huggingface/safetensors

  Simple, safe way to store and distribute tensors

  Language:Python2.8k189

• KEKE046/mlir-tutorial

  Hands-On Practical MLIR Tutorial

  Language:C++29740

• pabloariasal/modern-cmake-sample

  Example library that shows best practices and proper usage of CMake by using targets

  Language:CMake66672

• QidiLiu/project-example

  項目模板

  Language:Python1

• DefTruth/Awesome-LLM-Inference

  📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

  2.6k174

• NVIDIA/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++8.3k927

• immich-app/immich

  High performance self-hosted photo and video management solution.

  Language:TypeScript46.4k2.3k

• mit-han-lab/llm-awq

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

  Language:Python2.4k184

• IST-DASLab/gptq

  Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

  Language:Python1.9k151

• sshaoshuai/MTR

  MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.

  Language:Python663106

• ztxz16/fastllm

  纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

  Language:C++3.3k334

• bigscience-workshop/Megatron-DeepSpeed

  Ongoing research training transformer language models at scale, including: BERT & GPT-2

  Language:Python1.3k213

• karpathy/minGPT

  A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

  Language:Python19.9k2.5k

• flet-dev/flet

  Flet enables developers to easily build realtime web, mobile and desktop apps in Python. No frontend experience required.

  Language:Python11k426

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++65.6k9.4k

• Mycenae/PaperWeekly

  Papers for CNN, object detection, keypoint detection, semantic segmentation, medical image processing, SLAM, etc.

  27862

• HiveChat/hive-desktop

  🐝 A small LAN chat app

  Language:C++8318

• siboehm/ShallowSpeed

  Small scale distributed training of sequential deep learning models, built on Numpy and MPI.

  Language:Python894

• milahu/awesome-qt6

  172

• amhndu/SimpleNES

  An NES emulator in C++

  Language:C++4.8k1.1k

• daohu527/dig-into-apollo

  Apollo notes (Apollo学习笔记) - Apollo learning notes for beginners.

  2.3k703

• Visualize-ML/Book4_Power-of-Matrix

  Book_4_《矩阵力量》 | 鸢尾花书：从加减乘除到机器学习；上架！

  Language:Python8.6k1.3k

• PaddlePaddle/PaddleHub

  Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)【安全加固，暂停交互，请耐心等待】

  Language:Python12.7k2.1k

• facebookincubator/AITemplate

  AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

  Language:Python4.5k363

• nod-ai/pandas-mlir

  Bridging Pandas and MLIR ecosystems

  Language:C++171