Avoid MPS bfloat16 cross kernel in rot6d conversion#23
Open
lyonsno wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
torch.linalg.crossinrot6d_to_rotmatwith the equivalent elementwise 3D cross productWhy
On MPS with bfloat16 and fallback disabled,
torch.linalg.crosscan fail withRuntimeError: Failed to create function state object for: cross_bfloat. The explicit cross-product formula uses basic tensor operations, preserves dtype/device, and keeps the operation on-device for MPS bfloat16.This is separate from #22 and only addresses the
cross_bfloatcompatibility failure. It is not intended as a performance optimization.Tests
PYTORCH_ENABLE_MPS_FALLBACK=0 uv run --with pytest --python .venv/bin/python pytest tests/test_rot6d_mps_bf16.py -qPYTORCH_ENABLE_MPS_FALLBACK=0 .venv/bin/python - <<'PY' ... rot6d_to_rotmat(..., device='mps', dtype=torch.bfloat16) ... PY.venv/bin/python -m py_compile wilor_mini/models/vit.py tests/test_rot6d_mps_bf16.py