Skip to content
AMD Perf Kernel Integration Tests

persistent kernel version of the flash attention forward + FLOP calculation fix when seqlen_q != seqlen_k #300

Sign in to view logs

persistent kernel version of the flash attention forward + FLOP calculation fix when seqlen_q != seqlen_k

persistent kernel version of the flash attention forward + FLOP calculation fix when seqlen_q != seqlen_k #300

Run time

Learn about OS pricing on GitHub Actions
Job Run time
Runner-Preparation-AMD
1s
Check-File-Changes
14s
pre-commit (code formatting)
52s
Integration-Tests-AMD (self-hosted, gfx942)
2m 37s
3m 44s