PyPI page
Home page
Author:
quantumaikr
License:
Apache-2.0
Summary:
Single-header LLM inference engine with KV cache compression (7× compression at fp32 parity)
Latest version:
0.13.0
Optional dependencies:
build
|
pytest
|
twine
Downloads last day:
0
Downloads last week:
6
Downloads last month:
548
7-day smoothing