Metadata-Version: 2.4
Name: hyperloom-inference_optimizer
Version: 0.0.1
Summary: Placeholder release reserving the distribution name for the ROCm Hyperloom inference optimizer runtime; under development.
Author: Advanced Micro Devices, Inc.
License-Expression: MIT
Project-URL: Homepage, https://github.com/AMD-AGI/Hyperloom
Project-URL: Source, https://github.com/AMD-AGI/Hyperloom
Project-URL: Issues, https://github.com/AMD-AGI/Hyperloom/issues
Project-URL: Documentation, https://rocm.docs.amd.com/projects/hyperloom/en/latest/index.html
Keywords: placeholder,amd,rocm,hyperloom,inference,optimization
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# hyperloom-inference-optimizer (placeholder)

This release is a **placeholder** that reserves the `hyperloom-inference-optimizer`
distribution name on PyPI. It contains metadata only: no modules, no entry
points, and no runtime code.

The real project is **ROCm Hyperloom**, an autonomous agentic system that
optimizes end-to-end LLM inference workloads on AMD GPUs:

- Source: <https://github.com/AMD-AGI/Hyperloom>
- Documentation: <https://rocm.docs.amd.com/projects/hyperloom/en/latest/index.html>

Until the first functional release is published here, install the release wheel
from GitHub Releases:

<https://github.com/AMD-AGI/Hyperloom/releases>

## Status

Under development. Do not depend on version `0.0.1` for anything other than
name resolution.
