[QNN:Bugfix] Guard against Conv/DepthwiseConv promotion to int8 when quantized weight is missing - #4760
Open
Qxinyu wants to merge 1 commit into
Open
[QNN:Bugfix] Guard against Conv/DepthwiseConv promotion to int8 when quantized weight is missing#4760Qxinyu wants to merge 1 commit into
Qxinyu wants to merge 1 commit into
Conversation
…quantized weight is missing When a Conv/DepthwiseConv is listed in skip_quant_op_names but still surrounded by int8 tensors, _supportQuant previously returned true, causing the QNN Conv execution to dereference a null weight pointer and crash. Add quantized-weight checks mirroring the CPU backend fix. Also harden QNNConvolution/QNNConvDepthwise against null weight data from ConvolutionCommon::load / getConvParameters.
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
_supportQuantin QNNBackend to check that Conv/DepthwiseConv actually has quantized weight data before returning true, mirroring the CPU backend's_convHasQuantWeightguardQNNConvolutionandQNNConvDepthwisewith null checks onConvolutionCommon::load/getConvParametersreturn valuescreateWeightAndBiasreturn value inonEncodeto bail early on missing weightsTest plan
skip_quant_op_namescontaining a Conv op no longer crashes