decoder_input_ids/decoder_inputs_embeds missing in example inputs for hf_T5_base
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1k
- Forks
- 346
- PR merge metrics
- No merged PRs in 30d
Description
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
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Inspect torchbenchmark/util/framework/huggingface/basic_configs.py around line 281, which the issue identifies as the input-generation code. Reproduce the hf_T5_base eager-mode run with the provided example inputs, then verify that the generated inputs include the required decoder input and that execution completes without the reported error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- performance, testing
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 55/100