Torch seems to be running a lot faster than torch-mlir
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.9k
- Forks
- 736
- Avg merge
- 5d 22h
- Merged PRs (30d)
- 15
Description
Hi,
Not sure if I am running this correctly. Following the same instructions in the readme, I created this colab notebook. This may be of help to try and reproduce the issue.
Any suggestion would be appreciated.
Time taken by PyTorch: 0.097411 seconds
Time taken by torch-mlir: 10.072865 seconds
Contributor guide
No contributing guide indexed for this repository
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
Start by running the linked Colab notebook using the README instructions and verify the reported PyTorch and torch-mlir timings under the same conditions. Determine whether the discrepancy is reproducible and what compiler or execution stage accounts for it; the issue is complete when the cause and any required follow-up are documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, pytorch
- Domain
- compilers, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100