Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
isGPUAvailable()returnstrueon machines where the NVIDIA driver is installed but the CUDA toolkit libraries (e.g.libcublasLt.so.12) are missing or on the wrong version. This causes ONNX Runtime to throw at model load time and not at GPU detection time, making the failure hard to trace. #85Expected behavior
isGPUAvailable()should returntrueonly when the full CUDA stack is confirmed to be functional.Actual behavior
isGPUAvailable()returnstruebased on driver presence alone, then ONNX Runtime crashes at model initialization with a missing shared library error.Changes:
Replace shell-based detection with an actual ONNX Runtime CUDA session creation using a minimal valid ONNX model. This validates the full CUDA stack end-to-end