New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Feature Request] remove or add explanation about 'op_types.difference(OP_TYPES_TO_EXCLUDE)' in get_qnn_qdq_config #23459

Open

xieofxie opened this issue Jan 22, 2025 · 0 comments

Labels

ep:QNN feature request

xieofxie commented Jan 22, 2025

Describe the feature request

See

onnxruntime/onnxruntime/python/tools/quantization/execution_providers/qnn/quant_config.py

Line 192 in ff8465e

op_types_to_quantize=list(op_types.difference(OP_TYPES_TO_EXCLUDE)),

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

xieofxie added the feature request label

github-actions bot added the ep:QNN label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment