This repository has been archived by the owner on Aug 30, 2024. It is now read-only.
[BesTLA] Improve RTN quantization accuracy of int4 and int3 #558
Job | Run time |
---|---|
2m 58s | |
3m 22s | |
1s | |
6m 21s |
Job | Run time |
---|---|
2m 58s | |
3m 22s | |
1s | |
6m 21s |