Skip to content

Conversation

@lerman25
Copy link
Collaborator

This PR change the following:

  1. HNSW serialized dataset to an updated one, containing 1mil vectors - as preparation for multi - dataset
  2. Structure of python files in benchmarks/data - to enable orderly addition of new python files
  3. Download dataset template python file
  4. Generate multi dataset from single template python file
  5. Add missing int8-single file to serializer.py
  6. Add missing batch-iter int8 option to benchmark.yml

@lerman25 lerman25 requested review from alonre24 and meiravgri March 10, 2025 11:54
@lerman25 lerman25 changed the title Update uint8 single hnsw + structural changes Update int8 single hnsw + structural changes Mar 10, 2025
@codecov
Copy link

codecov bot commented Mar 10, 2025

Codecov Report

All modified and coverable lines are covered by tests ✅

Please upload report for BASE (main@5df57b2). Learn more about missing BASE report.
Report is 1 commits behind head on main.

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #601   +/-   ##
=======================================
  Coverage        ?   97.19%           
=======================================
  Files           ?      106           
  Lines           ?     5713           
  Branches        ?        0           
=======================================
  Hits            ?     5553           
  Misses          ?      160           
  Partials        ?        0           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@lerman25 lerman25 added this pull request to the merge queue Mar 10, 2025
Merged via the queue into main with commit 5a86c90 Mar 10, 2025
19 checks passed
@lerman25 lerman25 deleted the OmerInt8_Single_update_hnsw branch March 10, 2025 16:29
github-actions bot pushed a commit that referenced this pull request Mar 10, 2025
* Change dataset to 1 mil

* Change dataset to 1 mil batch

* change file

* change dataset url to 1mil all

* change dataset url to 1mil int8

* restructer python scripts in data, add int8 to serializer, add batch-iter-int8 to yml

(cherry picked from commit 5a86c90)
@github-actions
Copy link

Successfully created backport PR for 8.0:

github-merge-queue bot pushed a commit that referenced this pull request Mar 11, 2025
Update int8 single hnsw + structural changes (#601)

* Change dataset to 1 mil

* Change dataset to 1 mil batch

* change file

* change dataset url to 1mil all

* change dataset url to 1mil int8

* restructer python scripts in data, add int8 to serializer, add batch-iter-int8 to yml

(cherry picked from commit 5a86c90)

Co-authored-by: lerman25 <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants