# Dao-AILab/quack

A Quirky Assortment of CuTe Kernels

Repository: https://github.com/Dao-AILab/quack
Canonical: https://ross.abutalabs.com/products/quack
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-31T00:41:19+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 96, longevity 33
- inputs: {"age_days": 470, "days_push": 3, "days_rel": 26, "gap_med": 3.5, "n_releases_24m": 47}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1135, forks 150 (observed 2026-09-01T02:13:54.493212+00:00)

## What it is
QuACK is a collection of high-performance GPU kernels (RMSNorm, LayerNorm, softmax, cross-entropy, GEMM with epilogues) written in NVIDIA's CuTe-DSL for Python. It targets modern NVIDIA GPUs (Hopper and Blackwell) and offers optional JAX bindings.

## Use cases
- speed up rmsnorm and layernorm in pytorch training
- fast softmax and cross entropy kernels for llm training
- hopper and blackwell gemm with fused epilogue
- write custom cuda kernels in python with cute dsl
- use optimized kernels from jax
- get speed-of-light memory-bound kernels on h100

## When to choose
- you need fast fused normalization, softmax, or cross-entropy kernels on H100/B200/RTX 50 GPUs
- you want to prototype GPU kernels in Python using CuTe-DSL
- you want drop-in kernels with optional JAX bindings

## When to avoid
- you are on older GPUs like A100 or consumer pre-Ada cards
- you need CUDA versions below 12.9 or Python below 3.12
- you need a broad production-tested kernel library rather than a curated assortment

## Facets
- artifact type: library
- maturity: active
- function: gpu-computing, machine-learning, deep-learning
- domain: gpu-computing, machine-learning, deep-learning, developer-tools
- platform: python
- tags: cuda, cute-dsl, kernels, gemm, normalization, softmax, hopper, blackwell, jax, linux, gpu

## Member repositories
- Dao-AILab/quack (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:13:54.493212+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 2026-08-30T06:38:17.767314+00:00, confidence not recorded.
  - readme: https://github.com/Dao-AILab/quack (fetched 2026-09-01T02:13:54.493212+00:00, sha 10852241a891)
- Data as of 2026-08-30T08:39:29.467469+00:00.