Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

[QNN] Enable ConvTranspose + BatchNorm fusion after #23170

Aperta
  • Qualcosa non va?
#23,185 0 commenti 0 reazioni 1 assegnatario Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

@psiddh ci sta già lavorando.

Dal 28/9/2026.

Valutazione

Questa issue non è ancora stata valutata.

Descrizione

module: qnn partner: qualcomm
Feature and motivation

Enable ConvTranspose + BatchNorm fusion in the Qualcomm/QNN pass pipeline after #23170 lands.

FuseBatchNormWithConv.can_fuse currently rejects all transposed convolutions. This workaround avoids the incorrect output-channel scaling in the shared pass discussed in #22994. PR #23170 fixes that shared pass, including grouped transposed weights, but leaves the QNN guard in place. Consequently, QNN will continue to retain standalone BatchNorm operations after that fix.

Proposed work
  • Remove the transposed-convolution guard once #23170 is merged, reusing the corrected shared implementation. Update the subclass documentation or remove the redundant wrapper as appropriate.
  • Add Qualcomm regression cases for ConvTranspose + BatchNorm, covering equal and unequal input/output channel counts, grouped convolutions, and convolution bias enabled/disabled where supported by QNN.
  • Use nontrivial BatchNorm running statistics and affine parameters. Assert that BatchNorm is folded and the transformed output matches eager execution.
  • Run QNN delegation/execution coverage for the supported configurations and retain coverage for ordinary convolution fusion.
Additional context

Local CPU review validation of #23170 with PyTorch 2.13 passed all six new tests; four reproduce the original bug with the pre-fix pass. Eighteen additional grouped/depthwise ConvTranspose1d/2d/3d cases passed through the exported-program transform path. These checks validate the shared pass; QNN integration still needs the coverage above.

cc @cccclai @winskuo-quic @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin @abhinaykukkadapu @psiddh

Lingua principale
Python
Stelle
5k
Fork
1.2k
Merge medio
2g 7h
PR unite (30g)
521

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di pytorch/executorch

Tutte le issue di pytorch/executorch

Issue simili

Altre issue su Python

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.