Skip to content

perf(index)!: parallelize zone statistics computation in scalar index training - #8469

Merged
Xuanwo merged 13 commits into
lance-format:mainfrom
zhangyue19921010:parallel-zone-trainer-final
Nov 1, 2026
Merged

Xuanwo merged 13 commits into
lance-format:mainfrom
zhangyue19921010:parallel-zone-trainer-final

Conversation

@zhangyue19921010

@zhangyue19921010 zhangyue19921010 commented Aug 11, 2026 •

Copy link
Copy Markdown
Collaborator

Closes: #8468

@github-actions github-actions Bot added A-index Vector index, linalg, tokenizer performance labels Aug 11, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot added the K-changes Latest Gatekeeper recommendation requests changes. label Aug 11, 2026
@zhangyue19921010
zhangyue19921010 marked this pull request as draft August 11, 2026 12:40
@lance-gatekeeper lance-gatekeeper Bot removed the K-changes Latest Gatekeeper recommendation requests changes. label Aug 12, 2026
@zhangyue19921010
zhangyue19921010 marked this pull request as ready for review August 12, 2026 06:02
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot added K-approved Latest Gatekeeper recommendation permits acceptance. K-risk Latest Gatekeeper recommendation includes a non-blocking risk. labels Aug 12, 2026
@zhangyue19921010 zhangyue19921010 changed the title perf(index): parallelize zone statistics computation in scalar index training perf(index)!: parallelize zone statistics computation in scalar index training Aug 12, 2026
@lance-gatekeeper lance-gatekeeper Bot removed K-approved Latest Gatekeeper recommendation permits acceptance. K-risk Latest Gatekeeper recommendation includes a non-blocking risk. labels Aug 12, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot added the K-approved Latest Gatekeeper recommendation permits acceptance. label Aug 12, 2026
@codecov

codecov Bot commented Aug 12, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Aug 12, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot added K-approved Latest Gatekeeper recommendation permits acceptance. and removed K-approved Latest Gatekeeper recommendation permits acceptance. labels Aug 12, 2026
@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Aug 27, 2026
@lance-gatekeeper lance-gatekeeper Bot added the K-approved Latest Gatekeeper recommendation permits acceptance. label Aug 29, 2026
@zhangyue19921010

Copy link
Copy Markdown
Collaborator Author

Hi @Xuanwo CI passed and lance-gatekeeper approved. Would u mind to take a look? Thanks!

@lance-gatekeeper lance-gatekeeper Bot added K-approved Latest Gatekeeper recommendation permits acceptance. and removed K-approved Latest Gatekeeper recommendation permits acceptance. labels Aug 31, 2026
@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Sep 3, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot added the K-approved Latest Gatekeeper recommendation permits acceptance. label Sep 3, 2026
@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Sep 3, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot added the K-approved Latest Gatekeeper recommendation permits acceptance. label Sep 3, 2026
@zhangyue19921010

Copy link
Copy Markdown
Collaborator Author

Hold until zonemap v1 landed.

@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Sep 4, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Oct 12, 2026
lance-gatekeeper[bot]

This comment was marked as outdated.

@lance-gatekeeper lance-gatekeeper Bot removed the K-approved Latest Gatekeeper recommendation permits acceptance. label Nov 1, 2026

@lance-gatekeeper lance-gatekeeper Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ Gate recommendation: approve.

ZoneMap v1 is now merged into this base, satisfying the requested hold for v1. The updated trainers preserve aligned seed/scan zone boundaries and optional null tracking while retaining ordered, bounded parallel dispatch and the sequential trainer's borrowed, non-Send support.

@lance-gatekeeper lance-gatekeeper Bot added the K-approved Latest Gatekeeper recommendation permits acceptance. label Nov 1, 2026

@Xuanwo Xuanwo left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved on the verified head after hosted CI and Gatekeeper completed.

The change preserves the current-main aligned/null and ZoneMap V1/seed paths, retains the existing processor-based ZoneTrainer API, and adds ordered bounded parallel training with regression coverage. Training-only benchmark verification is limited to the measured 8M-row UTF-8, 64-fragment zonemap workload.

@Xuanwo
Xuanwo merged commit e51db34 into lance-format:main Nov 1, 2026
42 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

A-index Vector index, linalg, tokenizer breaking-change K-approved Latest Gatekeeper recommendation permits acceptance. performance

Projects

None yet

Development

Successfully merging this pull request may close these issues.

parallelize zone statistics computation in scalar index training

2 participants