Change invalid indices mask to -1 to save some cmp insts #109
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Outdated suggestions cannot be applied.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.
Hi,
Currently in your sparse prefill kernel, you validate the indices with two conditions: t >= 0 && t < params.s_kv.
Thats a bit redundant, because in real world scenarios it make more sense to pad it with -1. In addition, the generation and validation of indices should be done by indexer, not mla.
In your test_prefill when topk<indices, you cat 2147480000 to indices. If you change it to -1, you can save the comparation of && t < params.s_kv.