Skip to content

Introduce --memPoolSize to trtexec #703

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

Akado2009
Copy link
Contributor

Description
trtexec has a new parameter --memPoolSize, which was introduced as a substitute for --workspace (trtexec with workspace says that the parameters is DEPRECATED).
Link to official nvidia docs: trtexec

@Akado2009 Akado2009 requested a review from a team as a code owner April 23, 2025 15:23
Copy link

codecov bot commented Apr 23, 2025

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 85.67%. Comparing base (b13ef28) to head (f9dcde3).

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #703   +/-   ##
=======================================
  Coverage   85.67%   85.67%           
=======================================
  Files          99       99           
  Lines        7211     7211           
=======================================
  Hits         6178     6178           
  Misses       1033     1033           
Flag Coverage Δ
cpu-python3.10-unit-test 71.37% <ø> (ø)
cpu-python3.12-unit-test 71.37% <ø> (ø)
cpu-python3.7-unit-test 71.34% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@@ -104,7 +104,7 @@ def _preprocess(self):
# build options
'--explicitBatch',
f'--optShapes=input:{input_shape}',
'--workspace=8192',
'–-memPoolSize=8G',
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The --memPoolSize parameter in trtexec was introduced with TensorRT 8.5, which requires CUDA 11.4 or later.
Since we still support CUDA 11.1, we need to ensure compatibility with environments that do not have --memPoolSize available.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants