Prevent potential GPU OOM in R2C with split retry #14073

thirtiseven · 2025-12-31T02:19:17Z

Description

#13842 added retry for R2C convert to prevent Host OOM. Following on from that, this pr aimed to add split and retry for GPU OOM when copying the converted results to GPU.

This PR:

Introduced HostColumnarBatchWithRowRange, a wrapper for host columns that supports logical slicing without copying underlying host memory. This allows splitting a large host batch into smaller chunks for transfer.
Updated GpuRowToColumnarExec to use split and retry when a GPU OOM occurs during transfer.

Note that when we split a batch into two halves, we can't free them until both halves are processed. So, the first half just borrows the data, but we pass the ownership of the host columns to the second half. This ensures the host memory stays alive exactly as long as needed and is freed when the last split is closed.

Checklists

This PR has added documentation for new or modified features or behaviors.
This PR has added new tests or modified existing tests to cover new code paths.
(Please explain in the PR description how the new code paths are tested, such as names of the new/existing tests that cover them.)
Performance testing has been performed and its results are added in the PR description. Or, an issue has been filed with a link in the PR description.

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven · 2025-12-31T02:19:56Z

@greptile full review

Copilot

Pull request overview

This PR adds split retry functionality to Row-to-Columnar (R2C) conversion to prevent GPU out-of-memory (OOM) errors by implementing a mechanism to split batches in half when GPU OOM occurs during host-to-GPU data transfer.

Key Changes

Introduced a new HostColumnarBatchWithRowRange class that wraps host columns with row range tracking and supports splitting
Modified RowToColumnarIterator to use split retry logic for GPU OOM scenarios, allowing single input batches to produce multiple output batches
Added buildHostColumnsWithoutOwnership() method to transfer ownership of host columns to the retry framework

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
`sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala`	New class that wraps host columns with row range support, implements splitting logic for GPU OOM retry, and handles slicing of various column types (LIST, STRUCT, STRING, fixed-width)
`sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala`	Updated `RowToColumnarIterator` to build host columns separately, use split retry for TargetSize goals, and maintain a pending batch iterator for split outputs
`sql-plugin/src/main/java/com/nvidia/spark/rapids/GpuColumnVector.java`	Added `buildHostColumnsWithoutOwnership()` method to transfer host column ownership to caller
`tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala`	Added comprehensive test coverage for GPU OOM split retry scenarios including single batch requirement enforcement, multiple batch production, multiple consecutive splits, and single row edge case

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

greptile-apps · 2025-12-31T02:31:47Z

Greptile Overview

Greptile Summary

This PR adds GPU OOM protection during Row-to-Columnar host-to-GPU transfer by introducing split-and-retry capability. The implementation creates HostColumnarBatchWithRowRange, a zero-copy wrapper that enables logical slicing of host batches through reference counting, avoiding expensive memory copies during splits.

Key Implementation Details:

The solution separates the row-to-columnar conversion into two phases:

Host conversion (lines 688-694 in GpuRowToColumnarExec.scala): Builds host columns with retry-only support (no split)
GPU transfer (lines 708-724): Copies to GPU with full split-and-retry support via the new wrapper

Memory Management: Reference counting is correctly implemented throughout the lifecycle:

Initial creation increments refCount (line 60 in HostColumnarBatchWithRowRange.scala)
Split creates two new instances sharing underlying columns (lines 310-313), properly managing refCounts
Each batch decrements refCount on close (line 278), freeing memory when the last reference is released

Slicing Logic: The sliceHostColumn method (lines 112-233) handles all data types with proper offset normalization:

Fixed-width types: Direct memory slicing using pointer arithmetic
STRING/LIST: Offsets normalized to start at 0, with copied offset arrays
STRUCT: Recursive slicing of child columns
Validity: Reconstructed for the row range, optimized away if no nulls

Edge Case Handling: The implementation properly handles:

Empty strings (requires 1-byte dummy buffer, lines 186-194)
Zero columns/rows (early return, lines 67-69)
Single-row batches that cannot split (throws GpuSplitAndRetryOOM, lines 301-303)
RequireSingleBatch constraint (uses withRetryNoSplit, lines 696-706)

Iterator Pattern: The pendingBatchIter mechanism (lines 607-619) elegantly handles multiple output batches from a single input when splits occur, ensuring only one GPU allocation happens at a time.

Test Coverage: Comprehensive tests cover simple retry, split-and-retry, multiple consecutive splits, unsplittable edge cases, and complex nested data structures with nulls.

Confidence Score: 4/5

This PR is safe to merge with minimal risk, though thorough testing in production workloads is recommended due to the complexity of memory management
The implementation demonstrates solid software engineering with correct reference counting, proper resource cleanup, comprehensive edge case handling, and extensive test coverage. The split-and-retry logic integrates cleanly with the existing retry framework. Score is 4 (not 5) due to the inherent complexity of reference-counted memory management across split operations and the limited production testing of this specific code path (GPU OOM during transfer is relatively rare). The code quality is high with clear documentation and well-thought-out design.
No files require special attention - all three files show appropriate implementation quality and testing

Important Files Changed

File Analysis

Filename	Score	Overview
sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala	4/5	New file implementing zero-copy host column slicing with reference counting. Memory management is correctly implemented with proper incRefCount/close pairing. Edge cases for empty strings, null columns, and nested types are properly handled. Offset normalization for LIST/STRING types is mathematically correct.
sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala	4/5	Modified to use HostColumnarBatchWithRowRange for split-and-retry during GPU transfer. Introduced pendingBatchIter to handle multiple output batches from splits. Reference counting and iterator lifecycle management appear correct. RequireSingleBatch constraint properly throws GpuSplitAndRetryOOM when split is needed.
tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala	5/5	Comprehensive test coverage including simple retry, split-and-retry, multiple splits, edge cases (single row, empty schema), and complex nested types. Tests verify data integrity across splits and proper exception handling for unsplittable cases.

Sequence Diagram

sequenceDiagram
    participant Caller
    participant RowToColumnarIterator
    participant GpuColumnarBatchBuilder
    participant HostColumnarBatchWithRowRange
    participant RetryFramework
    participant GPU
    
    Caller->>RowToColumnarIterator: next()
    RowToColumnarIterator->>RowToColumnarIterator: buildBatch()
    RowToColumnarIterator->>GpuColumnarBatchBuilder: build rows on host
    GpuColumnarBatchBuilder-->>RowToColumnarIterator: hostColumns (refCount=1)
    RowToColumnarIterator->>HostColumnarBatchWithRowRange: create(hostColumns) [incRef to 2]
    Note over RowToColumnarIterator: withResource closes hostColumns [decRef to 1]
    RowToColumnarIterator->>RetryFramework: withRetry(hostBatch, splitPolicy)
    RetryFramework->>HostColumnarBatchWithRowRange: copyToGpu()
    HostColumnarBatchWithRowRange->>GPU: copy full batch
    GPU-->>HostColumnarBatchWithRowRange: GPU OOM!
    HostColumnarBatchWithRowRange-->>RetryFramework: throw GpuSplitAndRetryOOM
    RetryFramework->>RetryFramework: call splitPolicy(hostBatch)
    RetryFramework->>HostColumnarBatchWithRowRange: splitInHalf(hostBatch)
    Note over HostColumnarBatchWithRowRange: Create 2 splits [incRef to 3]<br/>Close original [decRef to 2]
    HostColumnarBatchWithRowRange-->>RetryFramework: [firstHalf, secondHalf]
    RetryFramework->>HostColumnarBatchWithRowRange: copyToGpu() on firstHalf
    HostColumnarBatchWithRowRange->>HostColumnarBatchWithRowRange: sliceHostColumn()
    Note over HostColumnarBatchWithRowRange: Create sliced view<br/>(shared data, copied offsets/validity)
    HostColumnarBatchWithRowRange->>GPU: copy sliced columns
    GPU-->>HostColumnarBatchWithRowRange: ColumnarBatch (success)
    HostColumnarBatchWithRowRange-->>RetryFramework: ColumnarBatch
    Note over RetryFramework: Close firstHalf [decRef to 1]
    RetryFramework-->>RowToColumnarIterator: Iterator[ColumnarBatch]
    RowToColumnarIterator->>RetryFramework: it.next() (get first)
    RetryFramework-->>RowToColumnarIterator: firstBatch
    RowToColumnarIterator->>RowToColumnarIterator: pendingBatchIter = remaining
    RowToColumnarIterator-->>Caller: firstBatch
    Caller->>RowToColumnarIterator: next() (second call)
    RowToColumnarIterator->>RetryFramework: pendingBatchIter.next()
    RetryFramework->>HostColumnarBatchWithRowRange: copyToGpu() on secondHalf
    HostColumnarBatchWithRowRange->>GPU: copy sliced columns
    GPU-->>HostColumnarBatchWithRowRange: ColumnarBatch (success)
    Note over RetryFramework: Close secondHalf [decRef to 0, free memory]
    RetryFramework-->>RowToColumnarIterator: secondBatch
    RowToColumnarIterator-->>Caller: secondBatch

greptile-apps

Additional Comments (1)

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala, line 176-184 (link)

logic: Workaround condition may not cover all cases. If dataLen == 0 but nullCount > 0 (empty strings with some null values), the code goes to the else branch and creates a 0-length slice, which could trigger the same copyToDevice issue mentioned in the comment.

_{4 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven · 2025-12-31T07:45:05Z

build

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven · 2025-12-31T10:44:44Z

build

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 5 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps

Additional Comments (1)

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala, line 178-188 (link)

style: Check that this empty string workaround handles all edge cases correctly. The 1-byte allocation when dataLen == 0 && nullCount == 0 works around copyToDevice behavior, but verify it handles: (1) all strings in slice are empty (not null), (2) mixed empty strings at different positions. This edge case could cause issues with certain data distributions.

_{4 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps

Additional Comments (1)

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala, line 180 (link)

syntax: typo: "Existsing" should be "Existing"

_{4 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps

Additional Comments (1)

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala, line 178-186 (link)

style: Consider if allocating a 1-byte dummy buffer for empty strings when dataLen == 0 but numRows > nullCount is necessary, or if cudf would accept null here to save allocations.

_{Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!}

_{4 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

sql-plugin/src/main/java/com/nvidia/spark/rapids/GpuColumnVector.java

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

firestarman · 2026-01-06T03:08:04Z

@greptileai can you review it again ?

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps

Additional Comments (1)

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala, line 180-188 (link)

style: Edge case handling for empty strings is correct: when dataLen == 0 but there are non-null rows (numRows > nullCount), allocates 1-byte buffer to satisfy cuDF requirements. However, consider validating that this 1-byte allocation doesn't cause issues if we're in a tight memory situation (though this is unlikely given the small size).

_{Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!}

_{4 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven · 2026-01-07T07:41:46Z

build

greptile-apps

Additional Comments (1)

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala, line 271-282 (link)

logic: Documentation claims split ownership transfer but implementation doesn't match - both splits increment reference count, so memory isn't transferred to last split as stated. Should the memory ownership transfer logic be implemented, or should the documentation be corrected to reflect the current reference counting approach?

_{3 files reviewed, 1 comment}

_{Edit Code Review Agent Settings | Greptile}

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven · 2026-01-07T07:53:38Z

build

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala

Signed-off-by: Haoyang Li <[email protected]>

firestarman · 2026-01-08T02:15:26Z

Overall looks good to me. But nice to have more eyes on this.

abellina · 2026-01-08T02:15:48Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

+ * @param numRows The number of rows in this range
+ * @param dataTypes The Spark data types for each column
+ */
+class HostColumnarBatchWithRowRange private (


Should we add the slice functionality to cuDF instead of spark-rapids?

Yes, it looks more natural to put it in cuDF Java. I would prefer to do it as a follow-up PR, but happy to do it right now.

@revans2 any preference?

Discussed with Bobby that it would be nice to have this long term in cuDF, but it's ok to start here.

abellina · 2026-01-08T02:19:52Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

+          numInputRows += rowCount
+          ret
+        } else {
+          val it = RmmRapidsRetryIterator.withRetry(


nit, import RmmRapidsRetryIterator.withRetry, like it was done for withRetryNoSplit

abellina · 2026-01-08T02:21:14Z

@thirtiseven I should have time to look at this tomorrow, if it can wait until then.

abellina · 2026-01-09T16:44:52Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

+    totalOutputBytes += GpuColumnVector.getTotalDeviceMemoryUsed(batch)
+    totalOutputRows += batch.numRows()
+    if (totalOutputRows > 0 && totalOutputBytes > 0) {
+      targetRows =


should we call this "nextBatchTargetRows"?

abellina · 2026-01-09T16:47:27Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

+          // Return the first batch now and keep the iterator for subsequent output batches.
+          // This ensures we only transfer one split at a time (avoid multiple device allocations).
+          closeOnExcept(it.next()) { first =>
+            pendingBatchIter = it


should we check if it.hasNext before we set pendingBatchIter? e.g. set to None otherwise?

yes good catch

abellina · 2026-01-09T18:47:08Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala

+ *
+ * Memory management uses reference counting: each instance increments the reference count
+ * of the host columns on construction and decrements it on close. The host columns are
+ * freed when the last reference is closed.


we should add that validity and offset buffers are copied, not logically sliced, in this description.

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps

_{No files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}

thirtiseven · 2026-01-20T06:51:38Z

build

thirtiseven · 2026-01-22T06:42:16Z

Hi @abellina could you take another look?

nvauto · 2026-01-26T02:05:11Z

NOTE: release/26.02 has been created from main. Please retarget your PR to release/26.02 if it should be included in the release.

thirtiseven · 2026-02-02T09:55:28Z

build

abellina · 2026-02-02T16:21:59Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

-        if (totalOutputRows > 0 && totalOutputBytes > 0) {
-          targetRows =
-            GpuBatchUtils.estimateRowCount(targetSizeBytes, totalOutputBytes, totalOutputRows)
+        val dataTypes = localSchema.fields.map(_.dataType)


it would be better if this was a class val.

abellina · 2026-02-02T16:22:58Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

+          HostColumnarBatchWithRowRange(hostColumns, rowCount, dataTypes)
        }

+        if (localGoal.isInstanceOf[RequireSingleBatchLike]) {


localGoal match { case RequireSingleBatchLike => ... case => // other goals ... }

abellina · 2026-02-02T16:25:29Z

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuRowToColumnarExec.scala

+          // Return the first batch now and keep the iterator for subsequent output batches.
+          // This ensures we only transfer one split at a time (avoid multiple device allocations).
+          closeOnExcept(it.next()) { first =>
+            pendingBatchIter = if (it.hasNext) it else Iterator.empty


nit, could just set pendingBatchIter = it, without checking, since we should be gating all the other logic in that it.hasNext returns false

Split retry for R2C

6989cb9

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven requested a review from Copilot December 31, 2025 02:19

Copilot started reviewing on behalf of thirtiseven December 31, 2025 02:19 View session

Copilot AI reviewed Dec 31, 2025

View reviewed changes

greptile-apps bot reviewed Dec 31, 2025

View reviewed changes

style

5be1b56

Signed-off-by: Haoyang Li <[email protected]>

fix ut

9c8eb60

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven requested a review from Copilot December 31, 2025 12:37

Copilot started reviewing on behalf of thirtiseven December 31, 2025 12:38 View session

Copilot AI reviewed Dec 31, 2025

View reviewed changes

sameerz added the bug Something isn't working label Jan 4, 2026

thirtiseven added 2 commits January 4, 2026 15:41

address comments, copyrights

78759bd

Signed-off-by: Haoyang Li <[email protected]>

refactor

579df1f

Signed-off-by: Haoyang Li <[email protected]>

thirtiseven self-assigned this Jan 5, 2026

thirtiseven marked this pull request as ready for review January 5, 2026 07:28

greptile-apps bot reviewed Jan 5, 2026

View reviewed changes

wjxiz1992 changed the title ~~Prevent potiential GPU OOM in R2C with split retry~~ Prevent potential GPU OOM in R2C with split retry Jan 5, 2026

ai comment address

53f2257

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps bot reviewed Jan 5, 2026

View reviewed changes

typo

3af43ab

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps bot reviewed Jan 5, 2026

View reviewed changes

firestarman reviewed Jan 5, 2026

View reviewed changes

address comments

4241572

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps bot reviewed Jan 6, 2026

View reviewed changes

revert copyright

b0c659c

thirtiseven requested a review from firestarman January 6, 2026 07:53

firestarman reviewed Jan 7, 2026

View reviewed changes

tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala Show resolved Hide resolved

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala Outdated Show resolved Hide resolved

firestarman reviewed Jan 7, 2026

View reviewed changes

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala Outdated Show resolved Hide resolved

firestarman reviewed Jan 7, 2026

View reviewed changes

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala Outdated Show resolved Hide resolved

address comments

50c1403

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps bot reviewed Jan 7, 2026

View reviewed changes

update comments

834310f

Signed-off-by: Haoyang Li <[email protected]>

firestarman reviewed Jan 7, 2026

View reviewed changes

sql-plugin/src/main/scala/com/nvidia/spark/rapids/HostColumnarBatchWithRowRange.scala Outdated Show resolved Hide resolved

tests/src/test/scala/com/nvidia/spark/rapids/RowToColumnarIteratorRetrySuite.scala Show resolved Hide resolved

update comments

4aed584

Signed-off-by: Haoyang Li <[email protected]>

abellina reviewed Jan 8, 2026

View reviewed changes

abellina reviewed Jan 9, 2026

View reviewed changes

address comments

e8305ed

Signed-off-by: Haoyang Li <[email protected]>

greptile-apps bot reviewed Jan 12, 2026

View reviewed changes

thirtiseven requested a review from abellina January 23, 2026 01:13

thirtiseven changed the base branch from main to release/26.02 January 26, 2026 06:52

abellina reviewed Feb 2, 2026

View reviewed changes

thirtiseven changed the base branch from release/26.02 to main February 3, 2026 02:09

Prevent potential GPU OOM in R2C with split retry #14073

Are you sure you want to change the base?

Prevent potential GPU OOM in R2C with split retry #14073

Conversation

thirtiseven commented Dec 31, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Checklists

Uh oh!

thirtiseven commented Dec 31, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Key Changes

Reviewed changes

Uh oh!

greptile-apps bot commented Dec 31, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Greptile Overview

Greptile Summary

Confidence Score: 4/5

Important Files Changed

Sequence Diagram

Uh oh!

greptile-apps bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Additional Comments (1)

Uh oh!

thirtiseven commented Dec 31, 2025

Uh oh!

thirtiseven commented Dec 31, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

greptile-apps bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Additional Comments (1)

Uh oh!

greptile-apps bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Additional Comments (1)

Uh oh!

greptile-apps bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Additional Comments (1)

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

firestarman commented Jan 6, 2026

Uh oh!

greptile-apps bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Additional Comments (1)

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

thirtiseven commented Jan 7, 2026

Uh oh!

greptile-apps bot left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

thirtiseven commented Dec 31, 2025 •

edited

Loading

greptile-apps bot commented Dec 31, 2025 •

edited

Loading

greptile-apps bot left a comment •

edited

Loading

greptile-apps bot left a comment •

edited

Loading

greptile-apps bot left a comment •

edited

Loading

greptile-apps bot left a comment •

edited

Loading

greptile-apps bot left a comment •

edited

Loading

greptile-apps bot left a comment •

edited

Loading