executorch
executorch copied to clipboard
Support Conv1d
Summary: Change the Conv1d Tests to use to_edge_transform_and_lower
This leverages and tests our new partitioner. One of the tests:
test_qs8_conv1d_with_floating_point_partitioner
was added by tarun, because wanted to validate quantized et models without delegating quantized op. So we must constant prop the weights (to apply quantization) and delegate only fp32, Turn our config mode the FP32, which allows us to only delegate fp32 ops.
Reviewed By: digantdesai
Differential Revision: D60323283