PyPI page
Home page
Author:
Mooncake Authors
Summary:
A KVCache-centric Disaggregated Architecture for large-scale LLM inference and training. (Non-CUDA version)
Latest version:
0.3.13.post1
Required dependencies:
aiohttp
|
msgpack
|
requests
|
typing-extensions
Downloads last day:
168
Downloads last week:
965
Downloads last month:
17,925
7-day smoothing