NVlabs/kda

Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.

Stars: 1.1k
Forks: 96
Open beginner issues: 0
Indexed issues: 1

Dominant language: No language data
License: No license data
Last GitHub push: Sep 14, 2026
Latest indexed: Sep 20, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

1 open issue indexed

[wishlist] Batched 128x128 SPD inverse with two epilogue products (Video Delta rule, VDN-H3 / SGLang PR #37903) Open

Difficulty 5/5 Over a week Newbie friendliness 28/100

NVlabs/kda#6 · Opened Sep 10, 2026

A short digest of beginner-friendly GitHub issues.