Skip to main content

autoxlstm

Automatic architecture configuration for xLSTM models — analogous to Hugging Face's AutoConfig, but for xLSTM.

autoxlstm picks the sLSTM/mLSTM block ratio, head count, and per-head matrix dimension automatically based on:

  • Task type: coding/math need sLSTM's sequential state tracking; text-generation/time-series favor mLSTM's parallel throughput.
  • Live GPU memory profiling: an empirical stress-test (sacrificial tensor allocation, catching torch.cuda.OutOfMemoryError) finds the largest safe matrix dimension before building the config, instead of guessing from a static formula.

Install

pip install -e .

## usage
```python
from autoxlstm import AutoXLSTMConfig

config = AutoXLSTMConfig().create(
    task_type="coding",
    context_length=2048,
    embedding_dim=512,
)

from xlstm import xLSTMBlockStack
model = xLSTMBlockStack(config)

Package Layout

File Responsibility
engine.py AutoXLSTMConfig orchestrator
profiler.py GPU inspection + OOM stress-test
policies.py task type → block-ratio (xlstm[N:1]) → slstm_at
dims.py pure num_heads/head_dim resolution
validators.py fail-fast input validation
exceptions.py custom error hierarchy
constants.py all tunable defaults

Release files for autoxlstm 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for autoxlstm 0.1.0
File Size Uploaded
autoxlstm-0.1.0.tar.gz 12.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for autoxlstm 0.1.0
File Interpreter ABI Platform
autoxlstm-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size:25.8 kB

Release files / autoxlstm-0.1.0.tar.gz

Download URL autoxlstm-0.1.0.tar.gz
Size 12.9 kB
Tags Source
SHA-256 checksum
How to use checksums
b5bbc54142e7f26464c55071a7d2cbbd12a8dafc5f6201bf0accf0e1364e1900
BLAKE2b-256 checksum
How to use checksums
8ee9d577294930818f6a2376de7db54c72287e0df27ed5c1637d5dfc4f3d2bff
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.6

Release files / autoxlstm-0.1.0-py3-none-any.whl

Download URL autoxlstm-0.1.0-py3-none-any.whl
Size 12.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6d259db09fedf3caf5fecc0691125eac4018ce4313330d53e3ec1b530e7e99dc
BLAKE2b-256 checksum
How to use checksums
49a2615680392524c65d56f48142b3988396afc1786abd4a067ecc4499d517f1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.6

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page