Will QNN-EP optimization work for a non X series snapdragon device?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 315
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 16
Description
As per qualcomm documentation https://docs.qualcomm.com/bundle/publicresource/topics/80-62010-1/ort-dml.html the QNN-EP, the DirectML-EP and the CPU-EP are provided for snapdragon X series. If i want to do PTQ+ AOT optimization for llama 3.2 1B model for 8 gen 3, can i still do that using olive?
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
The issue references Olive, Qualcomm's QNN-EP documentation, PTQ, AOT optimization, and the Llama 3.2 1B model. Start by checking the linked Qualcomm documentation and Olive's support for Snapdragon 8 Gen 3, then establish whether this workflow is supported and what guidance or documentation is missing.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100