Results 2 comments of XWH

the same question occured. Is there any way to use flexible shape? /coreML/lib/python3.11/site-packages/coremltools/converters/mil/frontend/torch/ssa_passes/torch_upsample_to_core_upsample.py", line 47, in _torch_upsample_to_core_upsample_block raise ValueError("Unable to map {} to core upsample".format(op.op_type)) ValueError: Unable to map torch_upsample_bilinear...

I encountered the same problem. I converted causalLM from coreml. There was no error during the conversion, but an error occurred during inference and it could not be located. `loc("/Users/xx/Library/Caches/python/com.apple.e5rt.e5bundlecache/24F74/949B0E364F41517D0F438CC20F342C46E47495D322383F351EE7D8E90ACB615D/54E9F2B14303BEF0A555D07775BA39A19B60E78FCAFDF5848B3ABBDF62F966E8.bundle/H16S.bundle/main/main_mps_graph/main_mps_graph.mpsgraphpackage/model_0.mpsgraph":0:0):...