Metal backend: int4 refactor checks and logs #17186
Open
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Outdated suggestions cannot be applied.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.
This pull request improves the
aoti_torch_mps__linear_fp_act_4bit_weightfunction in the Metal backend by adding comprehensive input validation for all tensors and enhancing debug logging. The changes ensure that tensor shapes, data types, and memory layouts are strictly checked before kernel execution, reducing the risk of runtime errors and making debugging easier.Input validation improvements:
A,B,S, andZtensors, including alignment requirements for dimensions and packed formats. Errors now provide detailed messages and return early if validation fails.Btensor's packed shape matches the expected calculation for 4-bit weights and that bothSandZtensors are 2D, have the correct leading dimension, and are contiguous.Debug logging enhancements: