A supported ANE-friendly llama model with good out-of-the-box performance and accuracy.
Open
Nobody has claimed this yet.
triaged
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
Make sure https://github.com/pytorch/executorch/tree/main/examples/apple/coreml/llama works well.
Integrate flow with etLLM: https://github.com/pytorch/executorch/blob/main/examples/models/llama/export_llama_lib.py
cc @iseeyuan
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
Start with examples/apple/coreml/llama and the integration flow in examples/models/llama/export_llama_lib.py. Determine what is needed for a supported ANE-friendly llama model, then verify that the flow works with etLLM and delivers good out-of-the-box performance and accuracy.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, mobile-dev
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100