Add unit tests for shared prefix masked attention with torch.FlexAttention
#358
Job | Run time |
---|---|
7s | |
11m 35s | |
10m 12s | |
21m 54s |
torch.FlexAttention
#358
Job | Run time |
---|---|
7s | |
11m 35s | |
10m 12s | |
21m 54s |