-
Notifications
You must be signed in to change notification settings - Fork 165
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add Text2ImagePipeline to llm bench #1129
Conversation
5ea79fe
to
a0c7a8b
Compare
@sbalandi could you please also add test run with --genai option in https://github.com/openvinotoolkit/openvino.genai/blob/master/.github/workflows/llm_bench-python.yml#L73 |
dreamlike-art/dreamlike-anime-1.0 is added @eaidova could you please confirm if it's okay, or too big ? I have also tried segmind/tiny-sd-mxfinetune , this model has supported type of scheduler, but it fails in scheduler.cpp on creating pipeline, because scheduler.json has value |
631d228
to
7f894f0
Compare
According to https://jsonlint.com/, it's invalid XML and I don't want to create WAs on GenAI for such cases (or only for popular models)
You can override scheduler to support one via |
okay, thank you |
@sbalandi for me, any variant of model is ok, until it works in GHA |
port to 2024.5 ? |
Ticket: CVS-156418