autoattn
Automatic routing between attention backends for LLMs/VLMs.
Install
pip install -e .
Usage
import torch
from autoattn import AutoAttention
attn = AutoAttention(d_model=256, num_heads=8, causal=True)
q = torch.randn(2, 128, 256)
k = torch.randn(2, 128, 256)
v = torch.randn(2, 128, 256)
out = attn(q, k, v) # Automatically picks best backend
Backends
| Backend | When Used | Memory | Exact? |
|---|---|---|---|
dense |
CPU, fallback | O(N²) | ✅ |
flash |
GPU, seq ≤ 2048 | O(N) | ✅ |
local |
GPU, seq > 4096, memory mode | O(N·W) | ❌ |
Modes
# Auto (default) - picks based on device/seq length
AutoAttention(d_model=256, num_heads=8, mode="auto")
# Performance - prefer flash on GPU
AutoAttention(d_model=256, num_heads=8, mode="performance")
# Memory - prefer local/sparse
AutoAttention(d_model=256, num_heads=8, mode="memory")
Requirements
- Python ≥ 3.9
- PyTorch ≥ 2.0
1 maintainer
Metadata
1 maintainer
Release files for autoattn 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| autoattn-0.1.0.tar.gz | 12.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| autoattn-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 23.3 kB
Release files / autoattn-0.1.0.tar.gz
| Download URL | autoattn-0.1.0.tar.gz |
|---|---|
| Size | 12.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c472d05d404595b4258bae1bd3373825122b19a45ad508a063db9a0b8dd52377
|
|
BLAKE2b-256 checksum How to use checksums |
4be0712dbeecbb73a7dae9fb61972c30b0f4ce388220c9851a51a9d65213cd88
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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 Dec 9, 2025.
Transparency logRelease files / autoattn-0.1.0-py3-none-any.whl
| Download URL | autoattn-0.1.0-py3-none-any.whl |
|---|---|
| Size | 10.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
05d4ea04136cae890734d90b7d78345afd1b917e8066d019aeaa9da347490c01
|
|
BLAKE2b-256 checksum How to use checksums |
9c6955b7ba7b1677803c1fedb557f00857f2921a86a45e61f86a0498ece42c1b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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 Dec 9, 2025.
Transparency log
