Comparisons to TensorFlow and pytorch impls make less sense than comparisons to onnxruntime imp,s
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
In my experience (though, for other models, CNN and visual transformer ones) onnxruntime provides better performance for inference on CPU than pytorch, tensor and (surprisingly) Apache TVM (CPU and Vulkan GPU backends, the models were "optimized"). So it may make little sense to compare CTranslate2 (which is targeted for fast inference) to framework targeted for convenient model design and training.
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
No file, test, or entry point is named. Start by locating the existing CTranslate2 performance comparisons and review how PyTorch, TensorFlow, and Apache TVM are used; done means updating the comparison scope or rationale to address ONNX Runtime as proposed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch, tensorflow
- Domain
- machine-learning, performance
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100