Increase corpus size by 90x #270
Merged
Conversation
This file contains 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
Remove unused logging statement
ganeshku1
previously approved these changes
Feb 5, 2025
dyastremsky
force-pushed
the
dyas-larger-corpus
branch
from
782a531 to
701bfae
Compare
nicolasnoble
approved these changes
Feb 5, 2025
cquil11
pushed a commit
to cquil11/perf_analyzer
that referenced
this pull request
Feb 5, 2025
Remove unused logging statement
cquil11
pushed a commit
to cquil11/perf_analyzer
that referenced
this pull request
Feb 5, 2025
Remove unused logging statement
lkomali
pushed a commit
that referenced
this pull request
Feb 5, 2025
Remove unused logging statement
tedzhouhk
pushed a commit
that referenced
this pull request
Feb 6, 2025
Remove unused logging statement
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Outdated suggestions cannot be applied.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.
As more users use GenAI-Perf to benchmark at the datacenter scale, increase the corpus size from 20k to 1.8M tokens (sample tokenization scheme: GPT2). This adds a modest overhead of .5s. This changes the corpus from all of Shakespeare's sonnets to his full set of works.
Also, add a warning if the number of tokens requested exceeds the corpus size.
New corpus size:
Pre-update time for 10 prompts with 1000 tokens:
Post-update time for 10 prompts with 1000 tokens:
Pre-update time for 100 prompts with 10000 tokens:
Post-update time for 100 prompts with 10000 tokens:
Warning when exceeding corpus size:
