南大2024操作系统课程实验

使用 CUDA C 实现的 llama 模型推理框架

NPUsim: Full-system, Cycle-accurate, Value-aware NPU Simulator

Documentation for HPC course

Curated collection of papers in machine learning systems

some knowleage about SystemC/TLM etc.

深度学习经典、新论文逐段精读

This is a Clang tool that parses SystemC models, and synthesizes Verilog from it.

Electronic System Level design cource@NCKU

This is a project created and completed by team BOOM(Beihang OO masters).This is a superscalar processor with a 13-stage out-of-order dual-emission architecture.

SystemC/TLM2.0 productivity library wrapping the Extendable Instruction Set Simulator ETISS as a tlm cpu core.

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

Architecting and Building High Speed SoCs, published by Packt

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

这是一个连载的博文系列，我将持续为大家提供尽可能透彻的Android源码分析

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Coyote is a simulator combining Spike and Sparta

QEMU libsystemctlm-soc co-simulation demos.

The ParaNut Processor - Highly Parallel and More Than Just a CPU Core

A throughput-oriented high-performance serving framework for LLMs

SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

A source-level simulator for multi-core system

SystemC TLM2 testbench using gtest framework.