Repository navigation
Arm backend: Expand list of ops without quant kernel - #24430
Merged
Merged
Conversation
The added ops will output fp32 fake tensors, even when the input is int8 which injects floating point tensors in the graph after quant folding. This is usually not enough to fail lowering, but can cause issues under certain conditions such as: - Some node inserts a node without qparams - The decorate_fp32_to_int32 pass sees a cast to int32 that is supposed to be int8->int32. Since neither qparams, nor correct meta is present, an fp to int cast is inserted into an otherwise quantized graph. Signed-off-by: Erik Lundell <erik.lundell@arm.com> Change-Id: Ie6fc299b04d060dedcf70817eae7c2fcb9015dce
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24430
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 5 PendingAs of commit 04dd1e1 with merge base 1169410 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Erik-Lundell
added
release notes: none
Erik-Lundell
added
partner: arm
zingo
approved these changes
Nov 2, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The added ops will output fp32 fake tensors,
even when the input is int8 which injects floating point tensors in the graph after quant folding.
This is usually not enough to fail lowering, but
can cause issues under certain conditions such as:
an fp to int cast is inserted into an otherwise
quantized graph.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani