Commit 0758007
bypass add and addRelu that have inputs from non-dq nodes
Summary:
The QuantFusion pass in crashes when an add node's inputs aren't dequantize_per_tensor ops. QAT model produces exactly this pattern.
The dequants_inputs list ends up empty, and get_args_and_kwargs_add() indexes [0].
Differential Revision: D1039495731 parent 5d07ce0 commit 0758007
1 file changed
Lines changed: 4 additions & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
620 | 620 | | |
621 | 621 | | |
622 | 622 | | |
| 623 | + | |
| 624 | + | |
623 | 625 | | |
624 | 626 | | |
625 | 627 | | |
| |||
633 | 635 | | |
634 | 636 | | |
635 | 637 | | |
| 638 | + | |
| 639 | + | |
636 | 640 | | |
637 | 641 | | |
638 | 642 | | |
| |||
0 commit comments