Skip to content

Commit ca917ba

Browse files
committed
docs: add changelog fragment for shared-observer pooling fix (#52)
1 parent 58890bb commit ca917ba

1 file changed

Lines changed: 1 addition & 0 deletions

File tree

changelog.d/52.fixed

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
Fix per-channel activation quantization crashing with a shape-mismatch `RuntimeError` on MaxPool/AvgPool/AdaptiveAvgPool layers whose shared observer spans an axis the pool shrinks (e.g. a spatial axis under a stride>1 pool). Axes pooling never touches (batch, channel) keep working as per-channel; only the specific unsafe axis falls back to per-tensor, with a warning explaining why and how to pick a safe axis instead.

0 commit comments

Comments
 (0)