Skip to content
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

Support QAT in QCOM qnn backend #6212

Open
cccclai opened this issue Oct 15, 2024 · 3 comments
Open

Support QAT in QCOM qnn backend #6212

cccclai opened this issue Oct 15, 2024 · 3 comments
Labels
module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm

Comments

@cccclai
Copy link
Contributor

cccclai commented Oct 15, 2024

🚀 The feature, motivation and pitch

Currently qnn quantizer only supports PTQ (post training quantization), and we'd like to enable QAT (quantization aware trainning) for better quantization support

Alternatives

Use PTQ

Additional context

No response

RFC (Optional)

No response
@cccclai cccclai added partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm module: qnn Related to Qualcomm's QNN delegate labels Oct 15, 2024
@cccclai
Copy link
Contributor Author

cccclai commented Oct 15, 2024

Hi @chiwwang, @navsud is our quantization expert and is also looking into QAT for qnn, maybe we can coordinate and enable QAT together.

@chiwwang
Copy link
Collaborator

Nice! ++ @chunit-quic , who is prototyping QAT in qnn quantizer.

@chiwwang
Copy link
Collaborator

We have a prototype #6222, which is more like kickoff for our discussions.
It might be incorrect.... QAT is really a new thing for us. So please feel free to advise and give directions! (And...what model is suitable for the 1st QAT target? We need some E2E verifications... 🤔 )

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
module: qnn Related to Qualcomm's QNN delegate partner: qualcomm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@cccclai @chiwwang