PR GPU tests

Add tensor parallelism for attention QKVO #3222

Sign in to view logs

Run time

Learn about OS pricing on GitHub Actions

Job	Run time
gpu-2.0.1 / pytest-gpu	3m 16s
gpu-2.1.0 / pytest-gpu	3m 33s
gpu-2.1.0-flash2 / pytest-gpu	3m 34s
gpu-latest / pytest-gpu	3m 34s
	13m 57s