[ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading

[ISCA'25] LIA: A Single-GPU LLM Inference Acceleration with Cooperative AMX-Enabled CPU-GPU Computation and CXL Offloading

LLM Inference analyzer for different hardware platforms

Nano vLLM

APEX+ is an LLM Serving Simulator

Note repository for studying Peripheral Component Interconnect Express (PCIe) and Compute Express Link (CXL).

Machine Learning Engineering Open Book

《Reinforcement Learning》读书学习与视频分享笔记

from MHA, MQA, GQA to MLA by 苏剑林, with code

A "device memory" enabling project encompassing tools and libraries for CXL, NVDIMMs, DAX, memory tiering and other platform memory device topics.

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

Learning Large Language Model (LLM）(大语言模型学习)

A curated list of open-source projects that help leverage CXL technology.

A fully-modern text-based browser, rendering to TTY and browsers

你还在为自己存放的VV表情包不够多，使用时觉得不够贴切而感到烦恼吗？快来试试这个项目吧！

NVIDIA Linux open GPU with P2P support

百度网盘命令行工具。The terminal utility for Baidu Network Disk.

Userspace code for the Microsemi PCIe switch

linux Device driver test code for practise

A pupil in the computer world.(Felix Fu)

Linux 内核文档中文翻译

A kernel module for the Microsemi PCIe switch

A simulator of Cache

使用 CLI 进行中科院计算所上网认证登陆