Collect some CS textbooks for learning.

Collect some CS textbooks for learning.

Splits single Nvidia GPU into multiple partitions with complete compute and memory isolation (wrt to performace) between the partitions

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

First open-source KVTC implementation (NVIDIA, ICLR 2026) -- 8-32x KV cache compression via PCA + adaptive quantization + entropy coding

UniCNet is a cycle-accurate simulator supporting effienct simulation for composable chiplet networks.

decrypt NVML debug log files

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

High Performance KV Cache Store for LLM

Cost-efficient and pluggable Infrastructure components for GenAI inference

NVLeak: Off-Chip Side-Channel Attacks via Non-Volatile Memory Systems [USENIX Security '23]

A tutorial for getting started with the Deep Learning Accelerator (DLA) on NVIDIA Jetson

https://github.com/eunomia-bpf homepage, documents and blogs

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

A comprehensive toolkit for GPU Communications Libraries performance testing and data analysis.

cluster data collected from production clusters in Alibaba for cluster management research

vArmor is a cloud native container sandbox system based on AppArmor/BPF/Seccomp. It also includes multiple built-in protection rules that are ready to use out of the box.

A book for Learning the Foundations of LLMs

Machine Learning Engineering Open Book

hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等

Using Persistent Memory Region in NVMe SSD to boost KVStore accessing

SMDK, Scalable Memory Development Kit, is developed for Samsung CXL(Compute Express Link) Memory Expander to enable full-stack Software-Defined Memory system