[serge] Fix 10 integration tests for model glm_ocr failing with output_mismatch (list output differs (10))#46986
Open
sergereview[bot] wants to merge 2 commits into
Open
[serge] Fix 10 integration tests for model glm_ocr failing with output_mismatch (list output differs (10))#46986sergereview[bot] wants to merge 2 commits into
glm_ocr failing with output_mismatch (list output differs (10))#46986sergereview[bot] wants to merge 2 commits into
Conversation
…tput_mismatch` (list output differs (10))
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
…tput_mismatch` (list output differs (10))
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: glm_ocr |
Contributor
CI recapDashboard: View test results in Grafana |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Original CI failure
1/1: 10 integration tests for modelglm_ocrfailing withoutput_mismatch(list output differs (10))tests/models/glm_ocr/test_modeling_glm_ocr.py::GlmOcrIntegrationTest::test_small_model_integration_test_batch[multi-gpu] (output_mismatch, seen 7/7)Relates to #46985
The GLM-OCR integration tests generate outputs consisting of repeated
<|image|>tokens instead of coherent text, indicating image features are not being processed.GlmOcrModelinmodular_glm_ocr.pycurrently inheritsGlm4vModel.__init__unchanged, which instantiatesGlm4vVisionModelandGlm4vTextModelrather than the OCR-specific subclasses. This patch overridesGlmOcrModel.__init__to buildGlmOcrVisionModelandGlmOcrTextModelso the correct vision/text architectures are used during generation.This change was produced automatically by serge from a CI failure report. The patch was generated by an LLM and applied by serge; review before merging.
serge
v0.1.0· model:moonshotai/Kimi-K2.7-Code· 27 LLM turns · 30 tool calls · 109.5s · 601838 in / 6474 out tokens