Add Pallas GPU decode attention in Maxtext inference #1369
Triggered via pull request
February 25, 2025 21:22
tohaowu
Status
Success
Total duration
28m 53s
Artifacts
–
RunTests.yml
on: pull_request
prelim
3s
gpu_image
/
Build and upload image (a100-40gb-4)
40s
gpu_unit_tests
/
run
5m 18s
gpu_integration_tests
/
run
7m 51s
tpu_unit_tests
/
run
19m 6s
tpu_integration_tests
/
run
6m 26s