You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit d263897
Browse filesBrowse the repository at this point in the historyBrowse files
Arm backend: Fix two control flow bugs (pytorch#16274)
Arm backend: Regularize submodules before processing them.
Add a function _regularize_submodule that contains special
handling needed for submodules. This mainly solves two problems:
- Buffers in submodules are (currently) handled differently depending
on whether they are from tracing or added in passes. The old solution
tried avoiding having to add a new meta field, but was brittle.
The new solution simply marks all all placeholders before passes.
- The pass pipeline assumes the dim_order of inputs and outputs to match
the actual dim_order (tosa_dim_order). We need to ensure this.
------------------------
Arm backend: Fix while quantization
The output of the while loop body can either re-enter
the body, or exit the while loop. Therefore, A and B
in the diagrambelow need to share the same quantization parameters.
A -> while ( RESCALE -> ... -> RESCALE -> ) -> B
Earlier tests happened to get equal qparams on the
input and output, but this is not the general case.
Signed-off-by: Erik Lundell <erik.lundell@arm.com>
0 commit comments