This repository has been archived by the owner on Aug 30, 2024. It is now read-only.
[BesTLA] First-token inference optimization #1013
Job | Run time |
---|---|
2m 11s | |
1m 31s | |
1m 48s | |
1m 22s | |
16m 22s | |
1m 20s | |
24m 34s |
Job | Run time |
---|---|
2m 11s | |
1m 31s | |
1m 48s | |
1m 22s | |
16m 22s | |
1m 20s | |
24m 34s |