Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
☆2,124Oct 29, 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.☆4,296Oct 17, 2026Updated last week
- Material for gpu-mode lectures☆6,929Sep 9, 2026Updated last month
- FlashInfer: Kernel Library for LLM Serving☆6,806Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,471May 17, 2026Updated 5 months ago
- Nano vLLM☆16,211Apr 26, 2026Updated 6 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.
- My learning notes for ML SYS.☆7,617Oct 21, 2026Updated last week
- A Datacenter Scale Distributed Inference Serving Framework☆8,409Updated this week
- Machine Learning Engineering Open Book☆19,630Updated this week
- GPU programming related news and material links☆2,399Jun 15, 2026Updated 4 months ago
- Study Notes for 《AI Systems Performance Engineering》☆105Jul 24, 2026Updated 3 months ago
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,135Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,341Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,315Updated this week
- A tutorial on modern GPU programming for machine learning systems☆1,372Updated this week
- 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.
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,582Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,845Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,911Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,335Aug 26, 2025Updated last year
- Development repository for the Triton language and compiler☆20,481Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,674Updated this week
- Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming☆830Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,224Updated this week
- A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.☆976Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A Quirky Assortment of CuTe Kernels☆1,183Oct 15, 2026Updated 2 weeks ago
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,164Updated this week
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)☆1,303Mar 24, 2026Updated 7 months ago
- ☆4,161Mar 11, 2026Updated 7 months ago
- Tile primitives for speedy kernels☆3,786Sep 12, 2026Updated last month
- how to optimize some algorithm in cuda.☆3,335Oct 11, 2026Updated 2 weeks ago
- A kernel library written in tilelang☆2,018Oct 14, 2026Updated 2 weeks ago
- Distributed Compiler and Optimized Parallel Kernels☆1,576Sep 18, 2026Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs☆95,852Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- State of the art inference performance with modern accelerators on Kubernetes☆5,073Updated this week
- An ML Systems Onboarding list☆1,148Feb 19, 2026Updated 8 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆599Updated this week
- Implement a reasoning LLM in PyTorch from scratch, step by step☆5,722Updated this week
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,483Oct 19, 2026Updated last week
- Fastest kernels written from scratch☆629Aug 15, 2026Updated 2 months ago
- NVIDIA curated collection of educational resources related to general purpose GPU programming.☆2,141Updated this week