Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
46 commits
Select commit Hold shift + click to select a range
8706aaf
feat: add partitioned Clifford algebra kernel
Concode0 Apr 30, 2026
8ad6c19
refactor: organize partitioned algebra internals
Concode0 May 1, 2026
abde2e8
test: add partitioned algebra verification coverage
Concode0 May 1, 2026
d4934ee
chore: move clifford module into core
Concode0 May 6, 2026
0c73bed
feat: add algebra kernel config factory
Concode0 May 6, 2026
0f6b6b8
feat: route algebra construction through factory
Concode0 May 6, 2026
d919b4f
chore: clean hydra algebra defaults
Concode0 May 6, 2026
c7333ca
test: add partitioned dense-reference coverage
Concode0 May 6, 2026
b9b9b1a
feat: constrain partitioned algebra defaults
Concode0 May 6, 2026
1d8a93f
test: add docstrings for test case
Concode0 May 6, 2026
788c564
test: add test case about tree-rejection and more signature
Concode0 May 6, 2026
70b9c3e
refactor: restructure core planning architecture
Concode0 May 13, 2026
9e3e631
refactor: clean-up the core architecture
Concode0 May 13, 2026
20e1bbb
feat: add layer-owned grade layouts to linear
Concode0 May 13, 2026
e82e0ea
feat: support compact grade layouts in layer norm
Concode0 May 13, 2026
c051115
feat: support compact grade layouts in blade selector
Concode0 May 13, 2026
2428413
feat: route attention through layer-owned feature grades
Concode0 May 13, 2026
62a0fc9
feat: thread compact feature grades through transformer blocks
Concode0 May 13, 2026
0c6d665
feat: start compact pipelines from embeddings
Concode0 May 13, 2026
6c7babd
refactor: derive versor grade indices from planner layouts
Concode0 May 13, 2026
2b2ab06
feat: add compact grade layouts to mother adapters
Concode0 May 13, 2026
20ffdc7
feat: expose static layer optimization plans
Concode0 May 13, 2026
ebe02ae
refactor: move optimization route planning to core
Concode0 May 13, 2026
399eea9
feat: add optimization route coverage reports
Concode0 May 13, 2026
743fef3
refactor: unify core grade planning interfaces
Concode0 May 13, 2026
901a138
feat: add compact core layout accessors
Concode0 May 13, 2026
96e8116
refactor: enforce core grade planning policy
Concode0 May 13, 2026
380f9c7
fix: avoid dense basis enumeration in planner
Concode0 May 13, 2026
70809bd
docs: clarify torch bitmask dimension limit
Concode0 May 14, 2026
fb46bb2
refactor: remove premature layer optimization coupling
Concode0 May 14, 2026
5a6f9ba
chore: add setuptools for compile
Concode0 May 14, 2026
a8b2a4d
fix: separate product planning from runtime buffers
Concode0 May 14, 2026
48e6c08
perf: cache core layout indices
Concode0 May 14, 2026
40d19c4
perf: narrow bivector exp simplicity checks
Concode0 May 14, 2026
fb9733c
fix: gather product lanes before broadcasting
Concode0 May 14, 2026
2d041b1
perf: vectorize grade energy metrics
Concode0 May 14, 2026
97cea79
perf: reduce dense analysis temporaries
Concode0 May 14, 2026
8557c21
fix: align wedge with exterior product
Concode0 May 14, 2026
859f2cc
fix: use exterior wedge in lattice volume
Concode0 May 14, 2026
a19a4b0
chore: raise python support floor to 3.10
Concode0 May 15, 2026
27ddd21
fix: support pairwise projected products
Concode0 May 15, 2026
ed806e4
feat: add framework product pipeline surfaces
Concode0 May 15, 2026
e9fd0a2
test: organize framework pipeline coverage
Concode0 May 15, 2026
8453f2f
bench: add framework pipeline benchmark
Concode0 May 15, 2026
6b7ee64
docs: document framework architecture
Concode0 May 15, 2026
2d1a612
Merge branch 'main' into feat/framework-core-architecture
Concode0 May 15, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/docs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ jobs:

- uses: actions/setup-python@v5
with:
python-version: "3.11"
python-version: "3.10"

- name: Install documentation dependencies
run: uv sync --group docs
Expand Down
8 changes: 4 additions & 4 deletions .github/workflows/tests.yml
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ jobs:

- uses: actions/setup-python@v5
with:
python-version: "3.11"
python-version: "3.10"

- name: Install core + sr + md17 + dev extras
run: uv sync --extra sr --extra md17 --extra dev
Expand All @@ -62,7 +62,7 @@ jobs:

- uses: actions/setup-python@v5
with:
python-version: "3.11"
python-version: "3.10"

- name: Install all task extras + dev
run: uv sync --extra sr --extra md17 --extra lqa --extra dev
Expand All @@ -88,7 +88,7 @@ jobs:

- uses: actions/setup-python@v5
with:
python-version: "3.11"
python-version: "3.10"

- name: Install all task extras + dev
run: uv sync --extra sr --extra md17 --extra lqa --extra dev
Expand All @@ -114,7 +114,7 @@ jobs:

- uses: actions/setup-python@v5
with:
python-version: "3.11"
python-version: "3.10"

- name: Install all task extras + dev
run: uv sync --extra sr --extra md17 --extra lqa --extra dev
Expand Down
8 changes: 4 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Versor: A PyTorch Framework for Geometric Algebra Deep Learning

[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) [![Python](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/) [![PyTorch](https://img.shields.io/badge/PyTorch-2.0+-ee4c2c.svg)](https://pytorch.org/) [![Docs](https://img.shields.io/badge/docs-MkDocs-brightgreen)](https://concode0.github.io/Versor/) [![DOI](https://zenodo.org/badge/1149480519.svg)](https://doi.org/10.5281/zenodo.18939518)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) [![Python](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) [![PyTorch](https://img.shields.io/badge/PyTorch-2.0+-ee4c2c.svg)](https://pytorch.org/) [![Docs](https://img.shields.io/badge/docs-MkDocs-brightgreen)](https://concode0.github.io/Versor/) [![DOI](https://zenodo.org/badge/1149480519.svg)](https://doi.org/10.5281/zenodo.18939518)

> **"There is a ceiling above standard Deep Learning that no one saw. Versor opens the door above it."**

Expand Down Expand Up @@ -59,7 +59,7 @@ For code examples of each innovation, see [docs/innovations.md](docs/innovations

## Installation

Versor requires Python 3.9+ and PyTorch.
Versor requires Python 3.10+ and PyTorch.

```bash
# Clone the repository
Expand All @@ -83,7 +83,7 @@ uv sync --extra all # everything

```python
import torch
from core.algebra import CliffordAlgebra
from core.runtime.algebra import CliffordAlgebra
from layers.primitives.rotor import RotorLayer
from layers.linear import CliffordLinear
from functional.activation import GeometricGELU
Expand Down Expand Up @@ -361,4 +361,4 @@ By releasing this under Apache 2.0, we provide a **perpetual, royalty-free paten
```

## Reference:
* Pence, T., Yamada, D., & Singh, V. (2025). "Composing Linear Layers from Irreducibles." arXiv:2507.11688v1 [cs.LG]
* Pence, T., Yamada, D., & Singh, V. (2025). "Composing Linear Layers from Irreducibles." arXiv:2507.11688v1 [cs.LG]
10 changes: 8 additions & 2 deletions __init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,14 +2,20 @@

__version__ = "1.0.0"

from core.algebra import CliffordAlgebra
from core.module import CliffordModule
from core.config import AlgebraConfig, make_algebra, make_algebra_from_config
from core.foundation.module import CliffordModule
from core.runtime.algebra import CliffordAlgebra
from core.runtime.context import AlgebraContext
from layers import CliffordLinear, RotorLayer

__all__ = [
"__version__",
"AlgebraConfig",
"AlgebraContext",
"CliffordAlgebra",
"CliffordModule",
"make_algebra",
"make_algebra_from_config",
"RotorLayer",
"CliffordLinear",
]
Loading
Loading