[NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】

倪海厦外门弟子，为往圣继绝学。传承中医，主要以倪海厦倪师人纪天纪为主，专攻经方，后期还有李可、胡希恕等国医老前辈授课内容。内含倪师人纪系列(非视频语音转文字，皆是倪师自编教材课本讲义) 自学顺序：针灸，黄帝内经，神农本草经，伤寒论，金匮要略五部教学课本PDF（请配合B站视频学习，搜索倪海夏即可） 自学笔记正在手打中...

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Repository for nvCOMP docs and examples. nvCOMP is a library for fast lossless compression/decompression on the GPU that can be downloaded from https://developer.nvidia.com/nvcomp.

FlashMLA: Efficient MLA decoding kernels

Run generative AI models in sophgo BM1684X

DeepSeek | 中文官网、DeepSeek网页版、API 调用和本地部署教程 | 最全使用指南~【2025年3月更新】轻松使用 DeepSeek 网页版，快速稳定、不卡顿，支持 DeepSeek R1、V3 以及 ChatGPT 4o、o1、o3 多种功能。 本指南提供全面的 DeepSeek 使用说明，包含DeepSeek 官网平替、DeepSeek网页版、API使用、DeepSee…

CUDA/Metal accelerated language model inference

LLM inference in C/C++

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

CPU inference for the DeepSeek family of large language models in pure C++

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

LLM training in simple, raw C/CUDA

Fully open reproduction of DeepSeek-R1

LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

📰 Must-read papers on KV Cache Compression (constantly updating 🤗).

STP Toolbox for Python

This is the accompanying code for our arxiv pre-print: "BoolNet: Minimizing the Energy Consumption of Binary Neural Networks"

Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket

A 2D Unity simulation in which cars learn to navigate themselves through different courses. The cars are steered by a feedforward neural network. The weights of the network are trained using a modi…

LightSeq: A High Performance Library for Sequence Processing and Generation

计算机类常用电子书整理，并且附带下载链接，包括Java，Python，Linux，Go，C，C++，数据结构与算法，人工智能，计算机基础，面试，设计模式，数据库，前端等书籍

一款定制化的Hexo博客主题

Several simple examples for popular neural network toolkits calling custom CUDA operators.