# wafer-ai/gpu-perf-engineering-resources

A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.

Repository: https://github.com/wafer-ai/gpu-perf-engineering-resources
Canonical: https://ross.abutalabs.com/products/gpu-perf-engineering-resources
Homepage: https://www.wafer.ai/
Language: Python
License Family: other
Last push: 2026-08-23T07:17:11+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 16
- inputs: {"age_days": 234, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2080, forks 229 (observed 2026-08-28T04:06:10.325644+00:00)

## What it is
A curated list of resources for learning AI/GPU performance engineering, ordered from GPU fundamentals through kernel optimization, inference engines, and distributed inference systems. It links to original papers, official documentation, and creator repositories rather than being a software tool itself.

## Use cases
- learn gpu performance engineering from scratch
- find resources on cuda kernel optimization
- understand how llm inference engines work
- study distributed inference and model parallelism
- learn triton and cutlass programming
- prepare for a gpu performance engineering role
- find papers on kv cache and speculative decoding

## When to choose
- you want a structured, ordered learning path from GPU basics to production inference
- you prefer primary sources like papers and official docs over tutorials
- you need a reference map of the inference serving stack (kernels, engines, distributed systems)

## When to avoid
- you need runnable code or a library rather than a reading list
- you want beginner-friendly step-by-step tutorials with exercises
- you are looking for general machine learning or data science resources outside GPU performance

## Facets
- artifact type: learning-resource
- maturity: active
- function: gpu-computing, llm-inference, benchmarking, machine-learning, developer-tools
- domain: gpu-computing, large-language-models, deep-learning, tutorials, performance, artificial-intelligence
- platform: python, cross-platform
- tags: awesome-list, curated-resources, cuda, triton, kernel-optimization, inference-serving, distributed-systems, profiling, gpu

## Member repositories
- wafer-ai/gpu-perf-engineering-resources (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.325644+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:03.033397+00:00, confidence not recorded.
  - readme: https://github.com/wafer-ai/gpu-perf-engineering-resources (fetched 2026-08-28T04:06:10.325644+00:00, sha beac0ea3a3a4)
  - homepage: https://www.wafer.ai/ (fetched 2026-08-29T10:36:07.166263+00:00, sha 3cd832f4d3b6)
- Data as of 2026-08-30T08:39:29.467469+00:00.