Support weight sharing in QNN GPU #2325

vjatoth-qti · 2026-02-08T18:17:55Z

Describe your changes

Add unit tests for this change.
Make sure all tests can pass.
Update documents if necessary.
Lint and apply fixes to your code by running lintrunner -a
Is this a user-facing change? If yes, give a description of this change to be included in the release notes.

olive/passes/onnx/static_llm.py

+                decoder_config_extra=decoder_config_extra,
+                composite_components=None,
+            )
+            return handler


olive/passes/onnx/static_llm.py

+            composite_components=list(zip(component_names, components)),
        )

+        return composite


Support weight sharing in QNN GPU

0c0236a

github-advanced-security bot found potential problems Feb 10, 2026

View reviewed changes