Gemma3: fix test #36820
Gemma3: fix test #36820
Conversation
|
Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. When it is ready for review, please click the |
|
This comment contains run-slow, running the specified jobs: This comment contains run-slow, running the specified jobs: models: ['models/gemma3'] |
|
run-slow: gemma3 |
|
This comment contains run-slow, running the specified jobs: This comment contains run-slow, running the specified jobs: models: ['models/gemma3'] |
|
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. |
ydshieh
left a comment
ydshieh
left a comment
There was a problem hiding this comment.
works for me as long as you are able to get it work on slow CI :-)
Thanks a lot
|
run-slow: gemma3 |
|
This comment contains run-slow, running the specified jobs: This comment contains run-slow, running the specified jobs: models: ['models/gemma3'] |
|
run-slow: gemma3 |
|
This comment contains run-slow, running the specified jobs: This comment contains run-slow, running the specified jobs: models: ['models/gemma3'] |
|
The failing test -> 'tests/models/gemma3/test_modeling_gemma3.py::Gemma3Vision2TextModelTest::test_model_parallel_beam_search' is not related to the PR and seems was broken always. I don't know if static cache + multi GPU ever worked with VLMs. In Gemma3 we can't turn off static cache, so will check later. Not big issue for now I hope Will merge to unblock others :) |
* fix test * require_read_token and public repo ids * flash-attn test uncomment * fix torchscript
3 participants
What does this PR do?
As per title, got a ping from our CI bot about it