Closed rilango closed 11 months ago
This issue reproducible in v0.3.0 too.
Hi @rilango, thank you for your detailed reproduction scripts.
In your codes, truncation occurs during wrapping npz payload to numpy array.
np.array([[output]], dtype=bytes)
When using the bytes
dtype, numpy removes trailing \x00
bytes. Therefore, for arbitrary bytes, it is required to use object
dtype.
https://triton-inference-server.github.io/pytriton/0.3.0/binding_models/#defining-inputs-and-outputs
This issue is stale because it has been open 21 days with no activity. Remove stale label or comment or this will be closed in 7 days.
This issue was closed because it has been stalled for 7 days with no activity.
Description
When a large array is converted to
npz
format and returned, the client received a truncated result.To reproduce
If relevant, add a minimal example so that we can reproduce the error, if necessary, by running the code. For example:
Observed results and expected behavior
Expected behavior:
Actual behavior:
Environment