add fp8 conversion kernel for transpose in column major format (#1493) #1113
| Job | Run time |
|---|---|
| 4s | |
| 2m 55s | |
| 10m 2s | |
| 8m 47s | |
| 8m 37s | |
| 15m 35s | |
| 17m 53s | |
| 5m 34s | |
| 2m 51s | |
| 10m 2s | |
| 8m 56s | |
| 8m 32s | |
| 15m 40s | |
| 17m 54s | |
| 5m 52s | |
| 2m 55s | |
| 10m 41s | |
| 9m 14s | |
| 8m 29s | |
| 15m 30s | |
| 18m 30s | |
| 5m 51s | |
| 2m 47s | |
| 10m 23s | |
| 8m 56s | |
| 8m 30s | |
| 15m 39s | |
| 18m 17s | |
| 5m 41s | |
| 2m 56s | |
| 10m 50s | |
| 8m 53s | |
| 8m 31s | |
| 15m 45s | |
| 18m 0s | |
| 5m 44s | |
| 15s | |
| 14s | |
| 14s | |
| 21s | |
| 13s | |
| 18s | |
| 13s | |
| 13s | |
| 19s | |
| 13s | |
| 18s | |
| 14s | |
| 16s | |
| 19s | |
| 20s | |
| 14s | |
| 16s | |
| 14s | |
| 19s | |
| 14s | |
| 19s | |
| 15s | |
| 15s | |
| 13s | |
| 19s | |
| 16s | |
| 19s | |
| 13s | |
| 14s | |
| 20s | |
| 15s | |
| 13s | |
| 14s | |
| 16s | |
| 14s | |
| 6h 0m 28s |