🦆 QuACK: A Quirky Assortment of CuTe Kernels 🦆
Kernels are written in the CuTe-DSL.
Installation
# For CUDA 12.9:
pip install tokenspeed-quack
# For CUDA 13.x:
pip install 'tokenspeed-quack[cu13]' --extra-index-url https://download.pytorch.org/whl/cu130
# Do not use uv for CUDA 13.x installs yet: it can race/install
# nvidia-cutlass-dsl[cu13] in the wrong order (NVIDIA/cutlass#3259):
# https://github.com/NVIDIA/cutlass/issues/3259
# Optional: install NVIDIA matmul heuristics for better untuned GEMM configs
pip install 'tokenspeed-quack[heuristics]'
# Optional: JAX bindings (pulls in jax and jax-tvm-ffi)
pip install 'tokenspeed-quack[jax]'
Requirements
- H100, B200/B300, or RTX 50 GPU
- CUDA toolkit 12.9+
- Python 3.12
Kernels 🐥
- 🦆 RMSNorm forward + backward
- 🦆 Softmax forward + backward
- 🦆 Cross entropy forward + backward
- 🦆 Layernorm forward + backward
- 🦆 Hopper gemm + epilogue
- 🦆 Blackwell gemm + epilogue
- 🦆 Blackwell GeForce gemm + epilogue
Usage
from quack import rmsnorm, softmax, cross_entropy
JAX bindings are also available for some kernels (see docs/jax.md):
from quack.softmax_jax import softmax
Documentations
- JAX interface — optional
jax+jax-tvm-ffibindings, seequack/softmax_jax.pyfor an example.
[2025-07-10] We have a comprehensive blogpost on how to get memory-bound kernels to speed-of-light, right in the comfort of Python thanks to the CuTe-DSL.
Performance
See our blogpost for the details.
Development
To set up the development environment:
pip install -e '.[dev]'
pre-commit install
# For CUDA 13.x:
pip install 'tokenspeed-quack[dev,cu13]' --extra-index-url https://download.pytorch.org/whl/cu130
# Do not use uv for CUDA 13.x installs yet; use pip instead.
# See https://github.com/NVIDIA/cutlass/issues/3259
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file tokenspeed_quack-0.6.4.post20260829.tar.gz.
File metadata
- Download URL: tokenspeed_quack-0.6.4.post20260829.tar.gz
- Upload date:
- Size: 848.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
897588ed465f09cca8d8f4ed79c84fc10493e645b53bbccbffd7eff69d418d87
|
|
| MD5 |
4231fe74e127acaabb85449f0bb4b9b8
|
|
| BLAKE2b-256 |
531ca11ab235ce01bef622d1439ba7861860d668d94af7d497e23d2f87dd7e8c
|
Provenance
The following attestation bundles were made for tokenspeed_quack-0.6.4.post20260829.tar.gz:
Publisher:
tokenspeed-quack.yml on lightseekorg/tokenspeed-third-party
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
tokenspeed_quack-0.6.4.post20260829.tar.gz -
Subject digest:
897588ed465f09cca8d8f4ed79c84fc10493e645b53bbccbffd7eff69d418d87 - Sigstore transparency entry: 2635458491
- Sigstore integration time:
-
Permalink:
lightseekorg/tokenspeed-third-party@414dcf3eb95d0ab8e006b9b6309cdd87fa5a8c99 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/lightseekorg
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
tokenspeed-quack.yml@414dcf3eb95d0ab8e006b9b6309cdd87fa5a8c99 -
Trigger Event:
workflow_dispatch
-
Statement type:
File details
Details for the file tokenspeed_quack-0.6.4.post20260829-py3-none-any.whl.
File metadata
- Download URL: tokenspeed_quack-0.6.4.post20260829-py3-none-any.whl
- Upload date:
- Size: 730.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fc846ce2d72aa76661d5c7d3026331e0ccc50d4de4674765cfbac7cb19f0880a
|
|
| MD5 |
ba3d7282a7baa9aff1f941c49c5951e5
|
|
| BLAKE2b-256 |
102675943cea6a4eb063e28ca04741cf2fcc6d3c810764e0ee731207c8cce59c
|
Provenance
The following attestation bundles were made for tokenspeed_quack-0.6.4.post20260829-py3-none-any.whl:
Publisher:
tokenspeed-quack.yml on lightseekorg/tokenspeed-third-party
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
tokenspeed_quack-0.6.4.post20260829-py3-none-any.whl -
Subject digest:
fc846ce2d72aa76661d5c7d3026331e0ccc50d4de4674765cfbac7cb19f0880a - Sigstore transparency entry: 2635458495
- Sigstore integration time:
-
Permalink:
lightseekorg/tokenspeed-third-party@414dcf3eb95d0ab8e006b9b6309cdd87fa5a8c99 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/lightseekorg
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
tokenspeed-quack.yml@414dcf3eb95d0ab8e006b9b6309cdd87fa5a8c99 -
Trigger Event:
workflow_dispatch
-
Statement type:
