Making large AI models cheaper, faster and more accessible
[Pipeline Middleware] Reduce comm redundancy by getting accurate output (#2232)
* move to cpu to avoid dead lock * get output by offsets Co-authored-by: Ziyue Jiang <ziyue.jiang@gmail.com>
Z
Ziyue Jiang committed
8b045b3c1f4e6b8bfae062f0318bd1481c881a10
Parent: 09c0102
Committed by GitHub <noreply@github.com>
on 1/3/2023, 5:43:57 AM