Making large AI models cheaper, faster and more accessible
[gemini] gemini mgr supports "cpu" placement policy (#1118)
* update gemini mgr * update chunk * add docstr * polish placement policy * update test chunk * update test zero * polish unit test * remove useless unit test
V
ver217 committed
7d14b473f0013e62f2e2d9ba60ac8e39d62eb5fb
Parent: f99f56d
Committed by GitHub <noreply@github.com>
on 6/15/2022, 7:05:19 AM