iquitap

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

netron

Visualizer for neural network, deep learning and machine learning models

paper-reading

深度学习经典、新论文逐段精读

mlc-llm

Universal LLM Deployment Engine with ML Compilation

carrot

Free ChatGPT Site List 这儿为你准备了众多免费好用的ChatGPT镜像站点

TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

bob-plugin-openai-translator

基于 OpenAI API 的文本翻译、文本润色、语法纠错 Bob 插件，让我们一起迎接不需要巴别塔的新时代！Licensed under CC BY-NC-SA 4.0

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.

Awesome-LLM-Compression

Awesome LLM compression research papers and tools.

LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

sparsegpt

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

hidet

An open-source efficient deep learning framework/compiler, written in python.

cudnn-frontend

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

lizzieyzy

LizzieYzy - GUI for Game of Go

composable_kernel

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

MatmulTutorial

A Easy-to-understand TensorOp Matmul Tutorial

relax

flash-llm

Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

ReadingList

Papers on Graph Analytics, Mining, and Learning

PET

PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections

tvm_gpu_gemm

play gemm with tvm

TileFlow

TileFlow is a performance analysis tool based on Timeloop for fusion dataflows

tvm.tl

An extention of TVMScript to write simple and high performance GPU kernels with tensorcore.

MGG_OSDI23

Artifact for OSDI'23: MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms.

LibShalom

gSampler

hidet-artifacts

This repository is the artifact of paper "Hidet: Task Mapping Programming Paradigm for Deep Learning Tensor Programs".

pruningSPMM

bob-plugin-openai-translator

基于 ChatGPT API 的文本翻译、文本润色、语法纠错 Bob 插件，让我们一起迎接不需要巴别塔的新时代！