microsoft / microsoft/onnxruntime

[Feature Request] remove or add explanation about 'op_types.difference(OP_TYPES_TO_EXCLUDE)' in get_qnn_qdq_config

Open
#23,459 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

ep:QNN feature request
Dominant language
C++
Stars
21.9k
Forks
4.2k
Avg merge
4d 11h
Merged PRs (30d)
184

Description

### Describe the feature request

See https://github.com/microsoft/onnxruntime/blob/ff8465eda45a5ab1259fc5f1091fd38a33b596c4/onnxruntime/python/tools/quantization/execution_providers/qnn/quant_config.py#L192

From Qualcomm doc, cast is supported? https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/SupportedOps.html

### Describe scenario use case

Cast op is not quantized for qnn

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with onnxruntime/python/tools/quantization/execution_providers/qnn/quant_config.py at the referenced get_qnn_qdq_config logic, then compare its excluded operation types with Qualcomm's SupportedOps documentation. Determine whether the Cast operation should be quantized or whether the code needs an explanation; done means the requested behavior or rationale is clearly reflected and verified.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.