Skip to content

Issue #4612 - add checks for error return types #4613

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.

Sign up for GitHub

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+5 −0
Open

Issue #4612 - add checks for error return types #4613

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
53eda47
added capture to the bug template (#4576)
MrGeva Sep 10, 2025
4eb81b1
Issue #4612 - add checks for error return types
grolysaini Nov 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .github/ISSUE_TEMPLATE/bug_report.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,4 +64,6 @@ Baremetal or Container (if so, version):

**Have you tried [the latest release](https://developer.nvidia.com/tensorrt)?**:

**Attach the captured .json and .bin files from [TensorRT's API Capture tool](https://docs.nvidia.com/deeplearning/tensorrt/latest/inference-library/capture-replay.html) if you're on an x86_64 Unix system**

**Can this model run on other frameworks?** For example run ONNX model with ONNXRuntime (`polygraphy run <model.onnx> --onnxrt`):
3 changes: 3 additions & 0 deletions quickstart/IntroNotebooks/onnx_helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,6 +86,7 @@ def predict(self, batch): # result gets copied into output
err = cudart.cudaMemcpyAsync(
self.d_input, batch.ctypes.data, batch.nbytes, cudart.cudaMemcpyKind.cudaMemcpyHostToDevice, self.stream
)
err = err[0] if isinstance(err, tuple) else err
if err != cudart.cudaError_t.cudaSuccess:
raise RuntimeError(f"Failed to copy input to device: {cudart.cudaGetErrorString(err)}")

Expand All @@ -100,11 +101,13 @@ def predict(self, batch): # result gets copied into output
cudart.cudaMemcpyKind.cudaMemcpyDeviceToHost,
self.stream,
)
err = err[0] if isinstance(err, tuple) else err
if err != cudart.cudaError_t.cudaSuccess:
raise RuntimeError(f"Failed to copy output from device: {cudart.cudaGetErrorString(err)}")

# synchronize threads
err = cudart.cudaStreamSynchronize(self.stream)
err = err[0] if isinstance(err, tuple) else err
if err != cudart.cudaError_t.cudaSuccess:
raise RuntimeError(f"Failed to synchronize stream: {cudart.cudaGetErrorString(err)}")

Expand Down