-
Notifications
You must be signed in to change notification settings - Fork 200
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.
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
Async kserve samples #1641
Async kserve samples #1641
Conversation
data.append(triton_client.async_infer( | ||
model_name=args.get( | ||
'pipeline_name') if is_pipeline_request else args.get('model_name'), | ||
inputs=inputs, | ||
outputs=outputs)) | ||
|
||
output = data[x].get_result().as_numpy(args['output_name']) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why for http there's a different approach than with grpc sample? This part calls async_infer method, but it looks like effectively it's synchronous as we call get_result() right after inference is scheduled.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There doesn't seem to be a callback equivalent in the http client https://github.com/triton-inference-server/client/blob/1a98fe0cd6b18ded726ada052f1bab06ab07ceb1/src/python/library/tritonclient/http/__init__.py#L1494
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You're right. Let's stick to this version then.
No description provided.