Quantize: specify each major tensor quant in CLI for common LLMs #14355
Job | Run time |
---|---|
2m 19s | |
9m 38s | |
3m 44s | |
2m 51s | |
2m 37s | |
1m 55s | |
17m 10s | |
9m 46s | |
10m 30s | |
2m 51s | |
2m 31s | |
3m 8s | |
2m 37s | |
3m 46s | |
1m 40s | |
1m 38s | |
1m 13s | |
1m 54s | |
2m 10s | |
1s | |
1m 36s | |
3m 5s | |
5m 13s | |
6m 21s | |
1s | |
5m 4s | |
1s | |
6m 59s | |
4m 29s | |
8m 33s | |
4m 11s | |
14m 26s | |
4m 53s | |
4m 5s | |
1s | |
59s | |
3m 44s | |
1s | |
3m 51s | |
2m 9s | |
1s | |
1s | |
2h 43m 43s |