mirror of https://github.com/llvm/torch-mlir
1201babb9f
- Refactors more "onnx.ReduceXXX" patterns through helper function. - Fixes bug with iterating unconditionally on `output_dim == 1` during `dimList` inference. This change results in passes for the following 11 models: crossvit_15_240 crossvit_15_dagger_240 crossvit_15_dagger_408 crossvit_18_240 crossvit_18_dagger_240 crossvit_18_dagger_408 crossvit_9_240 crossvit_9_dagger_240 crossvit_base_240 crossvit_small_240 crossvit_tiny_240 --------- Co-authored-by: Vinayak Dev <104419489+vinayakdsci@users.noreply.github.com> |
||
---|---|---|
.. | ||
ops | ||
simple_ops_a_to_f.mlir | ||
simple_ops_g_to_p.mlir | ||
simple_ops_q_to_z.mlir | ||
unsupported_fb_opt_ops.mlir |