# gpu-mode/resource-stream

GPU programming related news and material links

Repository: https://github.com/gpu-mode/resource-stream
Canonical: https://ross.abutalabs.com/products/resource-stream
Homepage: https://discord.gg/gpumode
License: MIT
License Family: permissive
Last push: 2026-06-15T04:57:18+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 70
- inputs: {"age_days": 980, "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 2303, forks 139 (observed 2026-08-28T04:06:35.634232+00:00)

## What it is
A community-curated collection of links to CUDA and GPU programming resources, including books, papers, blog posts, YouTube videos, tweets, and implementations. Maintained by the GPU MODE community, it also covers higher-level kernel development and performance optimization tools such as Triton and torch.compile().

## Use cases
- learn CUDA programming from scratch
- find a curated reading list for GPU kernel development
- discover CUDA tutorials, papers, and lecture videos
- learn Triton and GPU performance optimization
- resources for writing fast GPU kernels
- get started with GPU programming for machine learning systems

## When to choose
- You want a community-vetted starting point for learning CUDA and GPU programming
- You are looking for lectures, papers, and videos on kernel development and MLSys topics
- You want to follow a structured learning path from CUDA basics to advanced optimization with tools like Triton

## When to avoid
- You need runnable software, a library, or a tool rather than links to external resources
- You need official, authoritative NVIDIA documentation instead of community-curated links
- You need structured or machine-readable data, since the content is a markdown list of links

## Facets
- artifact type: learning-resource
- maturity: active
- function: gpu-computing, developer-tools
- domain: gpu-computing, machine-learning, awesome-lists, tutorials, developer-tools
- platform: cross-platform
- tags: cuda, gpu, triton, kernel-development, curated-list, performance-optimization, mlsys, torch-compile, nvidia, lectures

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:35.634232+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 2026-08-30T02:40:08.065764+00:00, confidence not recorded.
  - readme: https://github.com/gpu-mode/resource-stream (fetched 2026-08-28T04:06:35.634232+00:00, sha 0020774bda88)
  - homepage: https://discord.gg/gpumode (fetched 2026-08-29T10:20:39.844474+00:00, sha 368ffbcaba39)
- Data as of 2026-08-30T08:39:29.467469+00:00.