Trying to run torchbenchmark/models/hf_T5_base in eager mode with the provided example inputs yields this error:
RuntimeError: Execution of compiled model failed: You have to specify either decoder_input_ids or decoder_inputs_embeds
Edit1: From what I understand, this could be fixed by having whatever generated the inputs include decoder_input_ids as an identical copy of input_ids.
Edit2: Looks like this is the code that generates the inputs? https://github.com/pytorch/benchmark/blob/main/torchbenchmark/util/framework/huggingface/basic_configs.py#L281
Trying to run torchbenchmark/models/hf_T5_base in eager mode with the provided example inputs yields this error:
Edit1: From what I understand, this could be fixed by having whatever generated the inputs include
decoder_input_idsas an identical copy ofinput_ids.Edit2: Looks like this is the code that generates the inputs? https://github.com/pytorch/benchmark/blob/main/torchbenchmark/util/framework/huggingface/basic_configs.py#L281