Skip to content

[TRT] fix outdated module building method in tensorrt #16031

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.

Sign up for GitHub

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

Merged
masahi merged 1 commit into from
Nov 6, 2023
Merged

[TRT] fix outdated module building method in tensorrt #16031

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/how_to/deploy/tensorrt.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ regular TVM CUDA compilation and code generation.
.. code:: python

from tvm.relay.op.contrib.tensorrt import partition_for_tensorrt
mod, config = partition_for_tensorrt(mod, params)
mod = partition_for_tensorrt(mod, params)


Build the Relay graph, using the new module and config returned by partition_for_tensorrt. The
Expand All @@ -107,7 +107,7 @@ PassContext so the values can be read during compilation.
.. code:: python

target = "cuda"
with tvm.transform.PassContext(opt_level=3, config={'relay.ext.tensorrt.options': config}):
with tvm.transform.PassContext(opt_level=3):
lib = relay.build(mod, target=target, params=params)


Expand Down