Add benchmark to Flash README - #376
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a Benchmark section to the Flash package README: two figures, a token
table, and the measurement conditions.
Nine PDFs from 9 to 1,098 pages, each run end to end with tree optimization.
Time and cost both scale close to linearly with document length. The two things
the fit line does not show are called out in the text: cost tracks node count a
little more closely than page count, and wall clock flattens past roughly 700
pages where summary concurrency rather than length becomes the limit.
Figures live in
pageindex/flash/assets/so they travel with the package. Theseare the first tracked images in the repo; the top-level README uses external
URLs instead.
The numbers are tied to the model and concurrency they were measured with
(
gpt-5.6-luna, priced cold, no prompt-cache discount), so they will need are-run if either changes.