Modern GPU Programming For MLSys — Modern GPU Programming For MLSys
Machine learning systems sit at the heart of modern AI workloads. In these systems, performance often comes down to the quality of a small number of GPU kernels. Attention kernels, LLM prefill and decode kernels, low-precision block-scaled GEMMs, fused MoE layers, and other large fused kernels all directly shape end-to-end speed in both training and serving. To make these kernels fast, however, we need more than a list of optimization tricks. Modern GPUs are no longer simple variations of the same old design. Recent architectures introduce richer memory spaces, new access patterns, and increasingly specialized execution units. To program them well, we need both a clear mental model of the hardware and a practical understanding of how high-performance kernels are built. This book is about developing both. The book follows a simple progression: first understand the GPU hardware, then learn the programming model we will use, and finally build state-of-the-art kernels step by step. Our mai
Modern GPU Programming For MLSys# Machine learning systems power many of today’s AI workloads. As models grow and deployment settings become more complex, end-to-end performance increasingly depends on a small number of critical GPU kernels. Attention, LLM prefill and decode, low-precision block-scaled GEMM, fused MoE layers, and other large fused kernels directly affect both training and serving speed. Making these kernels fast requires more than a list of optimization tricks. Recent GPU architectures introduce richer memory spaces, new data-movement mechanisms, and increasingly…
saved by
related reading
- Modern GPU Programming For MLSys — Modern GPU Programming For MLSysmlc.ai
- How to Land a Frontier Lab Jobvladfeinberg.com
- Inside NVIDIA GPUs: Anatomy of high performance matmul kernels - Aleksa Gordićaleksagordic.com
- How To Scale Your Modeljax-ml.github.io
- [2410.20399] ThunderKittens: Simple, Fast, and Adorable AI Kernelsarxiv.org
- Look Ma, No Bubbles! Designing a Low-Latency Megakernel for Llama-1B · Hazy Researchhazyresearch.stanford.edu
- KernelBench: Can LLMs Write GPU Kernels?scalingintelligence.stanford.edu
- The Best GPUs for Deep Learning in 2023 — An In-depth Analysistimdettmers.com
- How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklogsiboehm.com
- GitHub - adam-maj/tiny-gpu: A minimal GPU design in Verilog to learn how GPUs work from the ground up · GitHubgithub.com
- GitHub - wafer-ai/gpu-perf-engineering-resources: A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.github.com
- Machine Learning System Resources | std::bodun::blogbodunhu.com