Repository navigation
Commit 43afe51
Vulkan: do not partition batch norm on a non-4d input
add_native_batch_norm_node() asserts
VK_CHECK_COND(in_sizes.size() == 4, "BatchNorm only support 4d tensor") on
both the input and the output sizes, but the partitioner claims the node at any
rank. A batch norm on rank-3 activations, which is every conv1d model, lowers
cleanly and then aborts at execute time.
Decline the node instead so it falls back.
Split out of pytorch#22399, which is now scoped to constant_pad_nd.1 parent a489948 commit 43afe51
1 file changed
Lines changed: 17 additions & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
1756 | 1756 | | |
1757 | 1757 | | |
1758 | 1758 | | |
| 1759 | + | |
| 1760 | + | |
| 1761 | + | |
| 1762 | + | |
| 1763 | + | |
| 1764 | + | |
| 1765 | + | |
| 1766 | + | |
| 1767 | + | |
| 1768 | + | |
| 1769 | + | |
| 1770 | + | |
| 1771 | + | |
| 1772 | + | |
| 1773 | + | |
| 1774 | + | |
1759 | 1775 | | |
1760 | 1776 | | |
1761 | 1777 | | |
1762 | 1778 | | |
1763 | 1779 | | |
1764 | 1780 | | |
1765 | 1781 | | |
| 1782 | + | |
1766 | 1783 | | |
1767 | 1784 | | |
1768 | 1785 | | |
| |||
0 commit comments