Skip to content

Arm backend: Add experimental support for new TOSAQuantizer#18100

Open
AdrianLundell wants to merge 4 commits intopytorch:mainfrom
AdrianLundell:change-1183485
Open

Arm backend: Add experimental support for new TOSAQuantizer#18100
AdrianLundell wants to merge 4 commits intopytorch:mainfrom
AdrianLundell:change-1183485

Conversation

@AdrianLundell
Copy link
Collaborator

@AdrianLundell AdrianLundell commented Mar 11, 2026

Allows initializing TOSA/EthosU/Vgf quantizers with use_composable_quantizer=True to use a new implementation of the quantizer following the Cortex-M. See
#17701 for more details.

  • Creates a new temporary TOSAQuantizer API layer for switching between the two versions
  • Adds a TOSAQuantizationConfig encapturing TOSA-specific qspec requirements for certain ops.
  • Adds quantizer_support.py for defining what operators are supported by the quantizer.
  • Align mark_node_as_annotated in cortex-m backend to TOSAQuantizer behaviour.
  • Update quantizer reporter to handle TOSA qspecs as they are dynamically created.

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell

Allows initializing TOSA/EthosU/Vgf quantizers with
use_composable_quantizer=True to use a new implementation of the
quantizer following the Cortex-M. See
pytorch#17701 for more details.

- Creates a new temporary TOSAQuantizer API layer for switching between
  the two versions
- Adds a TOSAQuantizationConfig encapturing TOSA-specific qspec
  requirements for certain ops.
- Adds quantizer_support.py for defining what operators are supported by
  the quantizer.
- Align mark_node_as_annotated in cortex-m backend to TOSAQuantizer
  behaviour.
- Update quantizer reporter to handle TOSA qspecs as they are
  dynamically created.

Signed-off-by: Adrian Lundell <adrian.lundell@arm.com>
Change-Id: Icbca66ff86e6f78ffa1c8dcec55e17c25f97d8ca
@AdrianLundell AdrianLundell added partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm ciflow/trunk release notes: arm Changes to the ARM backend delegate labels Mar 11, 2026
@pytorch-bot
Copy link

pytorch-bot bot commented Mar 11, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18100

Note: Links to docs will display an error until the docs builds have been completed.

❌ 2 New Failures

As of commit 5c02aa7 with merge base 096f10c (image):

NEW FAILURES - The following jobs have failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Mar 11, 2026
@zingo zingo added this to the 1.2.0 milestone Mar 11, 2026
Signed-off-by: Adrian Lundell <adrian.lundell@arm.com>
Change-Id: Id81e0c39d13a94a749206441fce60664c80a0af8
@zingo
Copy link
Collaborator

zingo commented Mar 11, 2026

Hi @SS-JIA / @digantdesai this adds a file, do you want/need to check this?
This is also something we would like to get into 1.2 is possible.

@AdrianLundell
Copy link
Collaborator Author

Fails unrelated

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

Labels

ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm release notes: arm Changes to the ARM backend delegate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants