text-generation-inference
e152cb02
- fix: also show total memory after full warmup
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
fix: also show total memory after full warmup
References
avoid-cuda-graph-during-warmup-if-oom
Author
drbh
Parents
8b4cd2a9
Loading