-
Notifications
You must be signed in to change notification settings - Fork 3.5k
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
[BYOC][TensorRT] Fixes for explicit batch mode, Support reduce to scalar, Support split op #7967
Conversation
@comaniac Could you please take a look? |
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
Thanks @trevor-m |
…lar, Support split op (apache#7967)
…lar, Support split op (apache#7967)
…lar, Support split op (apache#7967)
…lar, Support split op (apache#7967)
…lar, Support split op (apache#7967)
@@ -723,6 +723,53 @@ class ConcatOpConverter : public TensorRTOpConverter { | |||
} | |||
}; | |||
|
|||
class SplitOpConverter : public TensorRTOpConverter { |
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.
We should add #if TRT_VERSION_GE(5, 1, 5)
before it because the code uses params->network->addSlice
.
@@ -1072,6 +1127,7 @@ GetOpConverters() { | |||
map->emplace("expand_dims", std::make_shared<ExpandDimsOpConverter>()); | |||
map->emplace("squeeze", std::make_shared<SqueezeOpConverter>()); | |||
map->emplace("concatenate", std::make_shared<ConcatOpConverter>()); | |||
map->emplace("split", std::make_shared<SplitOpConverter>()); |
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.
It should go inside #if TRT_VERSION_GE(5, 1, 5)
block below
This PR has some bug fixes and new features for TRT BYOC.
use_implicit_batch=False
).