fix: prefer inplace softmax to avoid copy #2661
Merged
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Outdated suggestions cannot be applied.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 PR modifies
log_softmax
to operate in place, eliminating the need to copy large tensors. This optimization reduces memory consumption during warmup.For instance, when using
meta-llama/Meta-Llama-3.1-8B-Instruct
on an L4, this change allows running the model with--max-batch-prefill-tokens
increased from 7192 to 9874 without exceeding memory limits