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

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSys, etc. 🗃️ Llama3, Mistral, etc. 🧑‍💻 Video Tutorials.

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

A model compilation solution for various hardware

FedScale is a scalable and extensible open-source federated learning (FL) platform.

Machine Learning Framework for Operating Systems - Brings ML to Linux kernel

Deep Learning Energy Measurement and Optimization

A scalable & efficient active learning/data selection system for everyone.

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)

A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

Optimal Sparse Decision Trees

Materials for my 2021 NYU class on NLP and ML Systems (Master of Engineering).

📚FFPA: Yet antother Faster Flash Prefill Attention with O(1)⚡️SRAM complexity for headdim > 256, 1.8x~3x↑🎉faster than SDPA EA.

Federated Learning Systems Paper List

sensAI: ConvNets Decomposition via Class Parallelism for Fast Inference on Live Data

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

GraphSnapShot: Caching Local Structure for Fast Graph Learning [Efficient ML System]

[ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention