# gpu-mode/lectures

Material for gpu-mode lectures

Repository: https://github.com/gpu-mode/lectures
Canonical: https://ross.abutalabs.com/products/gpu-mode-lectures
Homepage: https://www.youtube.com/@GPUMODE
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2026-06-15T04:57:16+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 35, longevity 68
- inputs: {"age_days": 956, "days_push": 79, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6505, forks 649 (observed 2026-08-28T04:09:43.902351+00:00)

## What it is
A collection of supplementary materials (notebooks, slides, and code) for the GPU MODE lecture series on GPU programming and CUDA kernel development. It covers topics from CUDA fundamentals to advanced techniques like Flash Attention, quantization, and sparsity.

## Use cases
- learn CUDA programming from scratch
- optimize PyTorch kernels with CUDA or Triton
- understand GPU memory and compute architecture
- implement flash attention and ring attention
- profile and speed up deep learning workloads on GPUs
- study quantization and sparsity techniques for LLMs

## When to choose
- you want free, hands-on lecture material with runnable notebooks for GPU programming
- you are a Python developer learning to write and optimize CUDA kernels
- you want guided deep dives into attention mechanisms and PyTorch performance

## When to avoid
- you need production-ready GPU libraries rather than educational material
- you are looking for a tool or framework rather than tutorials
- you need structured courses with certifications or instructor support

## Facets
- artifact type: learning-resource
- maturity: active
- function: gpu-computing, machine-learning, developer-tools
- domain: gpu-computing, deep-learning, tutorials, education
- platform: python, cross-platform
- tags: cuda, triton, pytorch, jupyter-notebooks, kernel-optimization, lectures, flash-attention, profiling, gpu

## Member repositories
- gpu-mode/lectures (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.902351+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 2026-08-29T17:44:28.313084+00:00, confidence not recorded.
  - readme: https://github.com/gpu-mode/lectures (fetched 2026-08-28T04:09:43.902351+00:00, sha 7eb9f0680277)
  - homepage: https://www.youtube.com/@GPUMODE (fetched 2026-08-29T08:40:53.031280+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.