-
Notifications
You must be signed in to change notification settings - Fork 363
fix: bugs in TRT 10 upgrade #2832
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
Conversation
fa01628
to
62673bd
Compare
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.
LGTM
@@ -29,7 +29,7 @@ class PythonTorchTensorRTModule(Module): # type: ignore[misc] | |||
|
|||
def __init__( | |||
self, | |||
engine: trt.ICudaEngine, | |||
engine: trt.tensorrt.IHostMemory, |
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.
Lets use the bytes interface (may be just changing the type annotation), but we use the same thing for the C++ runtime
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.
Thanks. Currently, the engine
actually saves serialized engine
since TRT 10 changes API that uses builder.build_serialized_network
. Do you recommend saving deserialized engines or serialized engines?
Can this be merged @zewenli98 ? If so, please raise a cherry pick to release/2.3 it it's needed |
Description
Fix bugs in TRT 10 upgrade.
Fixes #2811
Type of change
Checklist: