Metadata-Version: 2.4
Name: aps-ai-beamline-controller
Version: 0.0.101
Summary: AI-driven Beamline Controller
Author-email: Luca Rebuffi <lrebuffi@anl.gov>
Maintainer-email: "XSD-OPT Group @ APS-ANL" <lrebuffi@anl.gov>
License-Expression: BSD-3-Clause
Project-URL: Homepage, https://github.com/APS-XSD-OPT-Group/AI-Beamline-Controller
Project-URL: Download, https://github.com/APS-XSD-OPT-Group/AI-Beamline-Controller
Keywords: dictionary,glossary,synchrotron,simulation
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: X11 Applications :: Qt
Classifier: Environment :: Console
Classifier: Environment :: Plugins
Classifier: Programming Language :: Python
Classifier: Operating System :: POSIX
Classifier: Operating System :: Microsoft :: Windows
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Visualization
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Developers
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: scikit-learn
Requires-Dist: torch==2.10.0
Requires-Dist: ax-platform==1.3.1
Requires-Dist: aps-beamline-driver>=1.0.72
Dynamic: license-file

# AI-Beamline-Controller
Ai-driven autonomous beamline controller

to insall run:

`pip install aps-ai-beamline-controller`

## NVIDIA Cuda and torch management

This package depends on torch, but the correct version must be found by:

1. running `nvidia-smi` to read the host's max CUDA version,
2. then mapping it to a `(torch release, CUDA build)` tier, 
3. pip install those exact wheels:

| driver CUDA | torch  | build |
|-------------|--------|-------|
| ≥ 13.0      | 2.12.1 | cu130 |
| 12.8–12.9   | 2.11.0 | cu128 |
| 12.6–12.7   | 2.12.1 | cu126 |
| 12.4–12.5   | 2.6.0  | cu124 |
| 11.8–12.3   | 2.6.0  | cu118 |
| none/older  | 2.12.1 | cpu   |
