PyPI page
Home page
License:
Apache-2.0
Summary:
MoE inference L2 hot-cache scheduler — run large MoE models on consumer GPUs
Latest version:
0.14.1
Required dependencies:
gguf
|
httpx
Optional dependencies:
sentence-transformers
Downloads last day:
14
Downloads last week:
162
Downloads last month:
965
7-day smoothing