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Outdated suggestions cannot be applied.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.
Description: Making chatting faster by removing small and big things.
Checklist:
Some benchmarks on my workload: (100 runs, but some are "hi" and some are "find intent/slots".
No change::
Removing deepcopy:
As we can see, there are still things that take time just like my last pull request #648 like
initial_string_from_tokens()
,tokens = [c["token"] for c in cache]
, having the hot-path execute last in the functions, using some mutable data structures when they're never modified (and recreating them). This was using a small model, I'll check with big model to see if they take more % time.What do you think ?