-
Notifications
You must be signed in to change notification settings - Fork 149
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
Inference TensorRT execution provider container revival #347
Conversation
@@ -604,6 +605,9 @@ def __init__( | |||
"trt_fp16_enable": True, |
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.
Question: is there any value from making that parametrised by env?
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.
Disabling this flag uniformly made inference slower even for unconverted models in my tests
@@ -1,5 +1,4 @@ | |||
FROM roboflow/roboflow-inference-server-trt-base:latest | |||
|
|||
FROM nvcr.io/nvidia/tensorrt:22.12-py3 |
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.
:+1
Description
Revives the trt container, bugfixing engine caching, and disables ORT graph optimizations (since trt can do them better)
Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Locally
Any specific deployment considerations
New container push
Docs