Offline DSI simulation: Immediate pruning #33
Merged
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
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Outdated suggestions cannot be applied.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 improves the accuracy of the offline DSI simulation by considering the following edge case where the first draft token of an iteration is rejected. This PR increases DSI speedups only slightly. The plots for
ndim=50in this setting do not change.The edge case: If the current iteration's first draft token is rejected, we do not necessarily need to incur the latency of drafting. We incur the latency of drafting only if we didn't incur the latency of verifying the previous iteration. Note that the edge case holds for the online DSI simulation.