Morphottention
Mathematical Morphology-based self-attention module for PyTorch using Flash-style kernel fusion.
Install
Prebuilt wheels are published for CPython 3.14 on Linux (x86_64, aarch64) and
Windows (x86_64). A working CUDA-enabled PyTorch (torch >= 2.12) must already
be installed in the environment.
pip install morphottention
Usage
The package exposes an nn.Module (MorphoAttention), a functional entry point
(morpho_attention), and the raw autograd bridge (MorphoAttentionFunction).
All inputs must be CUDA tensors; the module defaults to float16.
As an nn.Module
import torch
from morphottention import MorphoAttention
attn = MorphoAttention(
dim=256, # model dimension D
num_heads=8, # number of attention heads H
cube_m=16, # hypercube width per head
scale=1.0, # softmax temperature
causal=False, # casual masking flag
device="cuda",
)
x = torch.randn(2, 128, 256, dtype=torch.float16, device="cuda") # (B, N, D)
out = attn(x) # (B, N, D)
out.sum().backward()
Functional form
from morphottention import morpho_attention
out = morpho_attention(
x,
W_phi,
gate_q,
gate_k,
W_V,
num_heads=8, cube_m=16, scale=1.0,
causal=False,
)
Raw autograd bridge
import torch
from morphottention import MorphoAttentionFunction
B, N, D, H, cube_m = 2, 128, 256, 8, 16
x = torch.randn(B, N, D, dtype=torch.float16, device="cuda", requires_grad=True)
W_phi = torch.randn(D, H * cube_m, dtype=torch.float16, device="cuda", requires_grad=True)
gate_q = torch.ones(H, cube_m, dtype=torch.float16, device="cuda", requires_grad=True)
gate_k = torch.ones(H, cube_m, dtype=torch.float16, device="cuda", requires_grad=True)
W_V = torch.randn(D, D, dtype=torch.float16, device="cuda", requires_grad=True)
out = MorphoAttentionFunction.apply(
x, W_phi, gate_q, gate_k, W_V,
H, cube_m, 1.0, False, # num_heads, cube_m, scale, causal
) # (B, N, D)
out.sum().backward()
W_phi has shape (D, H * cube_m), W_V has shape (D, D), and gate_q /
gate_k each have shape (H, cube_m).
Building from source
Requires the CUDA 13.X toolkit (nvcc) and a matching torch build:
uv sync --package morphottention --no-dev --group build
uv build --package morphottention --wheel --no-build-isolation
License
MIT
Copyright © 2026 Vedran Hrabar.
1 maintainer
Metadata
1 maintainer
Release files for morphottention 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| morphottention-0.2.1.tar.gz | 19.8 kB | Details |
Built distributions (wheels)
Total release size: 270.8 MB
Release files / morphottention-0.2.1.tar.gz
| Download URL | morphottention-0.2.1.tar.gz |
|---|---|
| Size | 19.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
580343ed47707e22224a77599ee1652380afd65d67a367ff4d3467f2d65769f0
|
|
BLAKE2b-256 checksum How to use checksums |
7f9fa6a1bfdb85e8aaae3af0e72e61b9b10644732d7582cddaee6fe44a579fea
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp314-cp314-win_amd64.whl
| Download URL | morphottention-0.2.1-cp314-cp314-win_amd64.whl |
|---|---|
| Size | 193.7 kB |
| Tags | CPython 3.14 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
3ba555dbc16bcbb23652f1eccd9159d2adfca8550eb65be5b7a99badd36c637b
|
|
BLAKE2b-256 checksum How to use checksums |
8c3320454c7eaf6b2a6cb68b769a7da810a6ecb3cb4334e9cccba1dc81c4200d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | morphottention-0.2.1-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 46.2 MB |
| Tags | CPython 3.14 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
cc185a28cfb731a9c17d1ffe7be6b6cfb7dba2bfba6ec9f3c13b7293493494ce
|
|
BLAKE2b-256 checksum How to use checksums |
344eda168aad6c39041682e3e6c0d5e4b2bb9b025eab17dfece6423762664332
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl
| Download URL | morphottention-0.2.1-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl |
|---|---|
| Size | 43.9 MB |
| Tags | CPython 3.14 Linux glibc 2.24+ ARM64 Linux glibc 2.28+ ARM64 |
|
SHA-256 checksum How to use checksums |
2776eeab791dbb5c31b04d4bc2ea8f8a4d9a7a09cc09f244f5128ec02661a456
|
|
BLAKE2b-256 checksum How to use checksums |
584ad0105b19ec2f6b878ce56a1930d3133e912afd424ff58a73ee7a11503d39
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp313-cp313-win_amd64.whl
| Download URL | morphottention-0.2.1-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 191.7 kB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
a3c85c8ee5818767119e324e2bffda19df33810c8f3f754decc16359644f4656
|
|
BLAKE2b-256 checksum How to use checksums |
819832f7c0e0a922b211e7f2ee6053fc0e969edf1271fea0f184e5a9b2954f0e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | morphottention-0.2.1-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 46.2 MB |
| Tags | CPython 3.13 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
637bbd0beb7e1ddef48945e1b5d4d0b3b964a71d1996c11def2a72a6b79abb7b
|
|
BLAKE2b-256 checksum How to use checksums |
4467c956d90471b8c64c952ab1c0a245a522f4542ac3f174dae300671126cfca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl
| Download URL | morphottention-0.2.1-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl |
|---|---|
| Size | 43.9 MB |
| Tags | CPython 3.13 Linux glibc 2.24+ ARM64 Linux glibc 2.28+ ARM64 |
|
SHA-256 checksum How to use checksums |
a30ff72706d8805651c46a06762e531bcb98202062aac98c7548d5ff4d307f96
|
|
BLAKE2b-256 checksum How to use checksums |
ba340366c8f75b6e23363be0d2a61ec2f8eeb8093f9550c49614b6af18f95e79
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp312-cp312-win_amd64.whl
| Download URL | morphottention-0.2.1-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 191.7 kB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
d76be371b5f72ac9866105bcbe282a8477841b4a3da4bd8cda6d3c37f090a53e
|
|
BLAKE2b-256 checksum How to use checksums |
d0e16c152ee0828975832cda57fb404cc643246de7187d70d34da636cbdcb43b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl
| Download URL | morphottention-0.2.1-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 46.2 MB |
| Tags | CPython 3.12 Linux glibc 2.24+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
1ec02b1f7e7b66e1990b8619ced8ce6da803862473ec8f8a571fa0599a9d7bb8
|
|
BLAKE2b-256 checksum How to use checksums |
ceeacbfe8cd7b42073801e6c66f1e0266e73be88389b45f944063a95fd46e3e5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency logRelease files / morphottention-0.2.1-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl
| Download URL | morphottention-0.2.1-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl |
|---|---|
| Size | 43.9 MB |
| Tags | CPython 3.12 Linux glibc 2.24+ ARM64 Linux glibc 2.28+ ARM64 |
|
SHA-256 checksum How to use checksums |
ec591974a276f7200ad77cd7abd88269460860f66774d31d4d26b8125713d40f
|
|
BLAKE2b-256 checksum How to use checksums |
20813ce1721f2357106a3e550ee8b9165bd93039bc8f24bd2b8008bd09f82481
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 3, 2026.
Transparency log
