Metadata-Version: 2.4
Name: fabric-kv
Version: 0.0.1
Summary: Placeholder for BitPolar Fabric — KV cache compression plugin for vLLM. Real release coming soon.
Author-email: BitPolar <gehlot.21@gmail.com>
License: Apache-2.0
Project-URL: Homepage, https://bitpolar.dev
Project-URL: Repository, https://github.com/bitpolar/fabric-vllm
Project-URL: Documentation, https://bitpolar.dev/fabric
Project-URL: Changelog, https://github.com/bitpolar/fabric-vllm/blob/main/CHANGELOG.md
Keywords: llm,vllm,kv-cache,compression,inference,bitpolar,fabric
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# fabric-kv

> ⚠️ **0.0.1 is a name-reservation placeholder.** The real release is in active development.

**BitPolar Fabric** is a KV cache compression and transfer layer for LLM inference. The `fabric-kv` Python package will ship as a vLLM plugin delivering **12.8x KV cache compression at 0.96 quality** on Llama-3, with a one-line install:

```bash
pip install fabric-kv
```

## Status

| Phase | Status |
|---|---|
| Algorithm validated on A100 (833K vec/sec, 12.8x, 0.96) | ✅ Done |
| Wire format v1 freeze | 🚧 In progress |
| PyO3 bindings | ⏳ Planned |
| vLLM plugin | ⏳ Planned |
| Public launch | ⏳ ~5 weeks |

## Track Progress

- **Repo:** https://github.com/bitpolar/fabric-vllm
- **Blog:** https://bitpolar.dev/blog
- **Pitch deck:** https://bitpolar.dev/fabric

## License

Apache-2.0
