-
Notifications
You must be signed in to change notification settings - Fork 3.5k
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.
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
[Tracking Issue][ONNX] Quantized operator support in ONNX importer #8838
Comments
Adding @cconvey to the table who is working on |
@tmoreau89 - Can I try to implement |
@WenheLI absolutely, I'll mark you down |
Also CC- @kparzysz-quic |
Could you add Edit: we also have volunteers for com.microsoft.QGlobalAveragePool, com.microsoft.QGemm. You can add my name there, since folks need to create github accounts. |
@anwang2009 for com.microsoft.QLinearConcat |
Yes, yes, and yes! Thanks folks! |
Please add @tasmia-rahman for com.microsoft.MulInteger. |
Please add @FranckQC for com.microsoft.ReduceSumInteger |
Hi everyone. |
Done and done, thanks all! |
Hi All, May I sign up for QLinearSigmoid? Thank you. |
Hi @tmoreau89, I would like to sign up for com.microsoft.MatMulInteger16. Could you please assign it on my name? Thanks. |
Hi @tmoreau89, could you please add me for com.microsoft.QGemm?
|
Hi @tmoreau89, May I sign up for com.microsoft.QLinearLeakyRelu as well? (This is for a team member who needs to create github accounts). |
Could you please assign the op QLinearLeakyRelu on my name |
Yes, please reassign com.microsoft.QGemm to @rasagna-quic. |
Yes, @tmoreau89, could you please assign com.microsoft.QLinearLeakyRelu to |
I think I have it updated with the assignments as volunteered in the comments. Thanks, everyone! |
I'll grab com.microsoft.QuantizeLinear @tmoreau89 @kparzysz-quic |
Thanks @jcoplin-quic I've added you |
QLinearMatMul now has a PR: #8952 |
Thanks @cconvey - I've updated the table! |
I am referring this file to see what all ops would get quantized by ONNXRT. https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/quantization/registry.py @mbrookhart : As per your suggestion I have added this link, if you meant this resource to be added in the ticket please add it there as well. |
@avquicinc excellent point and many thanks for digging into the registry. I agree that the focus here is to shortlist these ops to the set defined in the registry. To use the example of |
Hi @tmoreau89, I've placed a PR #9028 for QLinearSigmoid. Just FYI. |
Thanks @arangasa - I've added it to the table! |
Also happy to share that |
@tmoreau89 Thanks for your help in reviewing the AveragePool op support quickly. Shall I pick up the com.microsoft.DynamicQuantizeMatMul op next to work on, if no one else has started working on that. If that's an urgently needed op, I can pick something else as well |
@quic-sanirudh please go ahead and pick |
…ear (#9028) * [ONNX][#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear
…izeLinear (apache#9028) * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear
Hi @tmoreau89 , I've raised #9186 for |
Thanks @abhikran-quic , added |
QLinearMatMul support is now merged! Thank you @cconvey for completing this task |
@WenheLI and @gayatripk1, is support for |
com.microsoft.QLinearLeakyRelu is already merged. |
Thank you I somehow failed to catch it, I'm adding #9063 to the table, thank you for your contributions. |
Hi @tmoreau89 I would like to work on |
Thank you @onkar-sima-ai I entered you in the table. |
Hi @tmoreau89 , I'd like to work on |
* [ONNX] QLinearLeakyRelu contrib op * Add comment * jostle ci * jostle ci
…izeLinear (apache#9028) * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear * [ONNX][apache#8838] QLinearSigmoid contrib op and Bug Fix for DequantizeLinear
* [ONNX] QLinearLeakyRelu contrib op * Add comment * jostle ci * jostle ci
Summary
This issue will be used to track ONNX importer coverage progress of standard and non-standard quantized ops in TVM, and can be used to coordinate distributed efforts on improving quantized importer coverage work across organizations.
Status
To this day (Aug 24th 2021) we'd like to account for both standard ONNX quantized ops and non-standard quantized contrib ops introduced by ONNXRT, as shown in the table below:
Shortlist of ops that are emitted by ONNXRT static quantization (higher priority), based on https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/quantization/registry.py:
Ops for supporting ORT dynamic quantization:
Other integer ops that might be relevant:
Other ops:
Coordination
Improving the importers can be a good onboarding task for engineers that would like to get a more in-depth exposure to the TVM stack. The goal is that if folks want to claim an operator they can feel reassured that their work won't be deprecated by work that is in flight.
We provide reference PRs that can serve as a template to adding a quantized standard op: #7802 by @mbrookhart. As well as non-standard op from the Microsoft ContribOperators set in ONNXRT: #8773 by @anwang2009.
Please comment in this issue if you'd like to add to Relay ONNX importer coverage so I can update the table.
cc @KJlaccHoeUM9l @ehsanmok
The text was updated successfully, but these errors were encountered: