Add Pallas GPU decode attention in Maxtext inference #1376
Triggered via pull request
February 25, 2025 23:06
tohaowu
Status
Success
Total duration
24m 25s
Artifacts
–
RunTests.yml
on: pull_request
prelim
4s
gpu_image
/
Build and upload image (a100-40gb-4)
43s
gpu_unit_tests
/
run
3m 16s
gpu_integration_tests
/
run
7m 59s
tpu_unit_tests
/
run
20m 35s
tpu_integration_tests
/
run
6m 30s