Open Daily: 10am - 10pm | Alley door pickup 10am - 7pm 3038 Hennepin Ave Minneapolis, MN
612-822-4611

  • Open Daily: 10am - 10pm
    Alley-side Pickup: 10am - 7pm

    3038 Hennepin Ave Minneapolis, MN
    612-822-4611

Open Daily: 10am - 10pm | Alley-side Pickup: 10am - 7pm
3038 Hennepin Ave Minneapolis, MN
612-822-4611
The GPU Performance Engineering Field Manual: Diagnose and Fix Slow, Costly AI Training and Inference with CUDA, PyTorch, and vLLM

The GPU Performance Engineering Field Manual: Diagnose and Fix Slow, Costly AI Training and Inference with CUDA, PyTorch, and vLLM

Lay, Steven S.

Paperback

General ComputersProgramming

ISBN13: 9798175092463
Publisher: Independently Published
Published: Sep 17 2026
Pages: 438
Weight: 2.22
Height: 0.89 Width: 8.50 Depth: 11.00
Language: English
When a training job crawls, a GPU sits idle, or an inference bill keeps climbing, this is the manual to open.

The GPU Performance Engineering Field Manual teaches a repeatable way to find out why AI workloads are slow or expensive, and how to prove that a fix worked. Every chapter starts from a symptom an engineer actually meets, explains the mechanism behind it, shows how to confirm the cause with measurements, and ends with the evidence that the problem is solved.

Inside you will learn how to:

  • Measure before you tune, with nvidia-smi, DCGM, the PyTorch Profiler, Nsight Systems, and a benchmark harness whose numbers you can defend
  • Fix a GPU that waits for data, out-of-memory failures, unstable mixed precision, and host overhead
  • Use torch.compile, CUDA graphs, attention kernels, and custom Triton and CUDA kernels where they pay off
  • Scale training with DDP, FSDP, NCCL, and tensor, pipeline, and expert parallelism, and diagnose slow or hung collectives
  • Understand LLM inference: prefill and decode, KV cache arithmetic, TTFT and inter-token latency
  • Tune vLLM batching, prefix caching, and chunked prefill, and apply quantization and speculative decoding safely
  • Scale, route, and autoscale serving fleets, hunt tail latency, and build cost models that turn performance into money
Built for ML engineers, platform and infrastructure engineers, and research engineers who train or serve models on NVIDIA GPUs with PyTorch. It assumes working Python and basic PyTorch, and no prior CUDA experience.

Practical tools on every page:

Also in

General Computers

View All