BLD: fix CPU Docker image and add non-publishing manual builds - #5524
Merged
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the CPU Dockerfile and its model requirements. Specifically, it upgrades the base Miniconda image to version 24.11.1-0 (Debian 12), replaces platform-specific ONNX Runtime dependencies with a single CPU-only onnxruntime==1.30.0 package, and updates text processing dependencies (nemo_text_processing, WeTextProcessing, and pynini) to versions compatible with Python 3.12. Additionally, a post-installation check has been added to verify that only the CPU execution provider is available in ONNX Runtime. There are no review comments, so no feedback is provided.
rogercloud
approved these changes
Sep 11, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
onnxruntime-gpu==1.16.0dependency withonnxruntime==1.30.0, which provides Python 3.12 CPU wheels. Assert CPU provider availability and CUDA provider absence during image construction.nemo_text_processing==1.1.0,WeTextProcessing==1.2.0, andpynini==2.1.6.post1. Require a binary Pynini distribution to avoid falling back to its unsupported legacy source build.The final image retains Python 3.12; the intermediate Python 3.11 downgrade was removed.
Validation
142caacfc2e258e8afe3128e5552b9200fa988eb: https://github.com/xorbitsai/inference/actions/runs/34610480052Full model inference and text-normalization runtime behavior have not been tested. GPU and ARM64 builds were not rerun for this branch.
Release note
This PR does not change the existing v3.4.0 tag. Rerunning that tag's old workflow will still use the old Dockerfile; publishing the fix requires a separate release decision after merge.