Repository navigation

[executorch][native-ggml] Compute cuBLAS GEMMs in f32 in the CUDA sample tests #66300

Job	Run time
gather-models	18s
Resolve CI docker image / resolve	51s
test-models-linux (buck2, mv3, portable, mt-l-x86iavx512-8-64, 90) / linux-job	8m 7s
test-models-linux (buck2, mv3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job	9m 40s
test-models-linux (cmake, vit, portable, mt-l-x86iavx512-8-64, 90) / linux-job	11m 6s
test-models-linux (cmake, mv3, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job	9m 47s
test-models-linux (cmake, mv3, portable, mt-l-x86iavx512-8-64, 90) / linux-job	10m 29s
test-models-linux (cmake, vit, xnnpack-quantization-delegation, mt-l-x86iavx512-8-64, 90) / linux-job	11m 15s
	1h 1m 33s