Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
☆1,963Sep 17, 2026Updated this week
Alternatives and similar repositories for ai-performance-engineering
Users that are interested in ai-performance-engineering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.☆3,210Sep 12, 2026Updated last week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,096May 17, 2026Updated 4 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,452Updated this week
- Material for gpu-mode lectures☆6,617Sep 9, 2026Updated last week
- GPU programming related news and material links☆2,332Jun 15, 2026Updated 3 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Nano vLLM☆15,518Apr 26, 2026Updated 4 months ago
- Open sources book with Modern CUDA Learn Notes for Beginners, includes FP16/BF16, FP8, HGEMM, FlashAttention, CuTe, etc.☆11,983Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,120Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,305Aug 26, 2025Updated last year
- My learning notes for ML SYS.☆7,368Sep 10, 2026Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆1,263Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,433Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆948Updated this week
- Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming☆810Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,457Updated this week
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,150Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,504Sep 12, 2026Updated last week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,170Updated this week
- A Quirky Assortment of CuTe Kernels☆1,147Updated this week
- Tile primitives for speedy kernels☆3,716Sep 12, 2026Updated last week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆1,250Mar 24, 2026Updated 5 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆586Aug 27, 2026Updated 3 weeks ago
- Distributed Compiler and Optimized Parallel Kernels☆1,546Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆4,064Mar 11, 2026Updated 6 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆203Feb 11, 2026Updated 7 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,614Updated this week
- A kernel library written in tilelang☆1,772Apr 23, 2026Updated 4 months ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,867Updated this week
- Achieve state of the art inference performance with modern accelerators on Kubernetes☆4,594Updated this week
- Fastest kernels written from scratch☆623Aug 15, 2026Updated last month
- Complete solutions to the Programming Massively Parallel Processors Edition 4☆868Sep 7, 2026Updated last week
- Perplexity GPU Kernels☆608Nov 7, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Learn CUDA with PyTorch☆483Updated this week
- NVIDIA curated collection of educational resources related to general purpose GPU programming.☆1,993Updated this week
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆369Updated this week
- A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.☆243Jun 29, 2026Updated 2 months ago
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆145Aug 15, 2026Updated last month
- Machine Learning Engineering Open Book☆19,013Sep 12, 2026Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆92,171Updated this week