Sync Gersbach Hep cleanser config compute-resource fixes to lineage-atlas snapshot#30
Open
adamklie wants to merge 1 commit into
Open
Sync Gersbach Hep cleanser config compute-resource fixes to lineage-atlas snapshot#30adamklie wants to merge 1 commit into
adamklie wants to merge 1 commit into
Conversation
The as-run config for the 2026_06_10/cleanser_initial run had three compute-resource fixes that were never committed and never mirrored into the CRISPRi_lineage_atlas/config snapshot: - google profile boot disk 100 GB -> 500 GB (anndata_concat overflowed the 100 GB task disk writing 47 temp_processed/*.h5ad, died at 44/47) - shared withName block n2-highmem-16 -> n2-highmem-32 (retry-scaled memory up to 200 GB overflowed the -16's 128 GB) - dedicated PreprocessAnnData override -> n2-highmem-64 / 320 GB*attempt (OOM-killed at every retry up to the 200 GB ceiling on Hep's 47 pools) Commits the modified setup/configs file and copies it verbatim into CRISPRi_lineage_atlas/config/v0.0.1/ so the lineage-atlas snapshot matches what actually produced the run. Hon was already in sync. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Commits and propagates the three compute-resource fixes that got the Gersbach WTC11 hepatocyte
cleanser_initialrun (2026_06_10) past its failure points. These were live in the as-runsetup/configsfile but uncommitted and not mirrored into theCRISPRi_lineage_atlas/configsnapshot — they'd be lost on a clean checkout.Fixes captured
anndata_concattemp_processed/*.h5adto the task disk; overflowed 100 GB, died at file 44/47 (No space left on device)withNameblock50GB×attempt, up to 200 GB) overflowed the -16's 128 GB; GCP rejected asmachine_type cannot satisfy compute_resourcePreprocessAnnData(new override)320GB×attemptcap 480Files
datasets/Gersbach…/setup/configs/…_cleanser_initial.config— commits the previously-uncommitted as-run configCRISPRi_lineage_atlas/config/v0.0.1/Gersbach…config— verbatim copy so the lineage snapshot matches what ranHon CM was already in sync (its lineage copy already carried the analogous PreprocessAnnData → n2-highmem-32 fix). Guide assignment itself completed (47/47); the run's actual wall is downstream at inference — not addressed here.
🤖 Generated with Claude Code