You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The T5 Text Encoder Model (from Stable Diffusion 3 pipeline) produces very different output when it is compiled & run on GPU using dynamic shapes, vs static shapes. Note that this issue seems to be specific to GPU -- I do not observe the same problem when using CPU.
OpenVINO Version
2025.1 Nightly (openvino_toolkit_windows_2025.1.0.dev20250214_x86_64)
Operating System
Windows System
Device used for inference
GPU
Framework
None
Model used
T5 Text Encoder
Issue description
The T5 Text Encoder Model (from Stable Diffusion 3 pipeline) produces very different output when it is compiled & run on GPU using dynamic shapes, vs static shapes. Note that this issue seems to be specific to GPU -- I do not observe the same problem when using CPU.
See reproduce steps below for more details.
Step-by-step reproduction
I have attached a small C++ reproducer:
t5_static_vs_dynamic_reproducer.zip
You should see the following at the end of the log, which indicates different output between static & dynamic:
Note that if you replace 'GPU' with 'CPU', no mismatches are reported.
Relevant log output
Issue submission checklist
The text was updated successfully, but these errors were encountered: