[integration/peerlab] Optimisation/quadtree memory optimisation - #36
Merged
Tobiaspk merged 19 commits intoMay 14, 2026
Merged
Conversation
Tobiaspk
force-pushed
the
optimisation/quadtree_memory_optimisation
branch
from
April 24, 2026 20:16
4ae5a37 to
7ab4b6e
Compare
Tobiaspk
changed the title
Collaborator
Author
|
WIP - still fails for Atera datasets |
Tobiaspk
force-pushed
the
integration/peerlab
branch
from
May 8, 2026 19:00
dc0846f to
b06f8d4
Compare
Collaborator
Author
|
Added batched logic for
Test-Script to ensure that results are identical (commit #5dd1ddb): test_batched_kdtree_neighbors.py Previous New |
Tobiaspk
force-pushed
the
optimisation/quadtree_memory_optimisation
branch
from
May 11, 2026 18:50
b16acc5 to
12a991c
Compare
Tobiaspk
added a commit
that referenced
this pull request
May 26, 2026
Major: CUDA/Xenium install #21: CUDA 12.1 support; Xenium v1 + binary column datatype support; pixi/conda install updates Reference gene correlation #32: Add custom reference gene correlation support via `--gene-corr-reference-path` Memory optimisations #36: GPU/memory optimisations for large datasets; chunked subgraphing fallback Large dataset fixes #44: Fix torch array overflow and related scaling issues Tiling fixes #42: Fix tiling/bincount errors and transcript thresholding Minor: Logging improvements #31: Improve debug logging; support `SEGGER_LOG_LEVEL` Margin handling #34: Warn instead of fail when tiling margins are too large Misc cleanup: Refactors; assertions/debugging; remove unused code and comments --------- Co-authored-by: Nandula Co-authored-by: Kalfus
EliHei2
pushed a commit
that referenced
this pull request
Jun 1, 2026
Major: CUDA/Xenium install #21: CUDA 12.1 support; Xenium v1 + binary column datatype support; pixi/conda install updates Reference gene correlation #32: Add custom reference gene correlation support via `--gene-corr-reference-path` Memory optimisations #36: GPU/memory optimisations for large datasets; chunked subgraphing fallback Large dataset fixes #44: Fix torch array overflow and related scaling issues Tiling fixes #42: Fix tiling/bincount errors and transcript thresholding Minor: Logging improvements #31: Improve debug logging; support `SEGGER_LOG_LEVEL` Margin handling #34: Warn instead of fail when tiling margins are too large Misc cleanup: Refactors; assertions/debugging; remove unused code and comments --------- Co-authored-by: Nandula Co-authored-by: Kalfus
EliHei2
pushed a commit
that referenced
this pull request
Jun 1, 2026
…imisation [integration/peerlab] Optimisation/quadtree memory optimisation
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
1 participant
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.
Closes #35
Optimising memory constraints for Segger:
Memory Changes
get_quadtree_kwargs(this crashed initially with 800GB memory)points.points.xy_points_in_polygons_containsOther
SEGGER_LOG_LEVEL=DEBUGdebuglevel logging overall--> Segger can now be run on an A100 with 250GB memory on the public Atera Breast Cancer Dataset.