[TRITON] Add attention sink support to Triton MHA kernels (#1576) #1
Annotations
2 errors
|
multi-gpu (aiter-mi355-8gpu)
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|
|
standard (aiter-mi355-1gpu)
The job has exceeded the maximum execution time while awaiting a runner for 24h0m0s
|