Add context-length sweep script for fragmentation analysis#49
Open
Beethom wants to merge 171 commits intomicrosoft:mainfrom
Open
Add context-length sweep script for fragmentation analysis#49Beethom wants to merge 171 commits intomicrosoft:mainfrom
Beethom wants to merge 171 commits intomicrosoft:mainfrom
Conversation
Docker setup for multiuser
Add vAttention fragmentation request metrics
…re the minimum number instead of actual number of blocks
…uests skipped saving metrics on requests that are ignored by the server
…ly-be-duped-by-manual-flush-and-shutdown removed manual flush endpoint
…d-blocks removed print statements and fixed incorrect number of blocks that we…
added fragmentation metrics
Adding client request loop
Mistral gqa to mla conversion
Sequential sweep over prompt sizes [128–32768 tokens] against a local vAttention server, logging per-request latency and status to JSONL. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
@Beethom please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
scripts/sweep_script.py: a sequential context-length sweep tool--fail-fastto abort on first error and--outputfor custom log pathTest plan
python scripts/sweep_script.py --model <model-name>--fail-fastwith a server that returns errors