Remove triton optimization config, causing error for multi gpu inference#2079
Merged
rapids-bot[bot] merged 3 commits intonv-morpheus:branch-25.02from Jan 10, 2025
Merged
Conversation
tzemicheal
added
improvement
hsin-c
approved these changes
Dec 11, 2024
tzemicheal
added
non-breaking
dagardner-nv
approved these changes
Jan 10, 2025
Contributor
|
/ok to test |
Contributor
|
/merge |
rapids-bot bot
pushed a commit
that referenced
this pull request
Jan 31, 2025
- Remove automatic TensorRT optimization from `all-MiniLM-L6-v2` config.pbtxt. This was causing segfault in `vdb_upload` example. - Triton issue: triton-inference-server/server#7885 - This [PR](#2079) removed optimization from `sid-minibert-onnx` and `phishing-bert-onnx` Closes #1649 ## By Submitting this PR I confirm: - I am familiar with the [Contributing Guidelines](https://github.com/nv-morpheus/Morpheus/blob/main/docs/source/developer_guide/contributing.md). - When the PR is ready for review, new or existing tests cover these changes. - When the PR is ready for review, the documentation is up to date with these changes. Authors: - Eli Fajardo (https://github.com/efajardo-nv) Approvers: - David Gardner (https://github.com/dagardner-nv) - Tad ZeMicheal (https://github.com/tzemicheal) URL: #2143
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
When running Triton inference for SID & Phishing detection pipeline using multi-gpu on
nvcr.io/nvidia/morpheus/morpheus-tritonserver-models:24.11. It result on segment fault. The TRT optimization line at the config.pbtxt of the models is causingtritonserver:24.11to fail with following error. This PR address the issue to run when all gpu is selected for inference.Closes #2028
By Submitting this PR I confirm: