Fix CPU LayerNormalization NaNs on large constant inputs #28440
Initial plan
0987816f
fix layer norm NaN on large constant inputs
1eb09397
add note for layer norm variance clamp
935888e3
document cpu-specific layer norm regression test
7a32e4f5
polish layer norm regression naming
24c9725b
document layer norm stability fix
2a738a00
copilot-swe-agent
changed the title [WIP] Fix NaN outputs in ONNX Runtime with large constant weights Fix CPU LayerNormalization NaNs on large constant inputs 68 days ago
justinchuby
marked this pull request as ready for review 59 days ago
Login to write a write a comment.
Login via GitHub