Translate gemma 4B recipes#404
Open
tanzeel-amd wants to merge 9 commits into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new Olive recipe for exporting and running the gated google/translategemma-4b-it multimodal translation model (text and image translation) via ONNX Runtime GenAI, including an optional WMT24++ + COMET benchmarking script.
Changes:
- Added end-to-end export pipeline (
builtin/optimize.py) plus Olive JSON configs to export text/vision/embedding ONNX sub-models. - Added runtime scripts for inference (
inference.py) and WMT24++ benchmarking (benchmark_wmt24pp.py). - Added recipe documentation and included the Gemma Terms of Use.
Reviewed changes
Copilot reviewed 12 out of 12 changed files in this pull request and generated 7 comments.
Show a summary per file
| File | Description |
|---|---|
| google-translategemma-4b-it/README.md | Documents export/inference/benchmark usage and model architecture. |
| google-translategemma-4b-it/LICENSE | Adds Gemma Terms of Use text to the recipe directory. |
| google-translategemma-4b-it/inference.py | CLI for text/image translation using ORT GenAI multimodal pipeline. |
| google-translategemma-4b-it/benchmark_wmt24pp.py | CLI to run WMT24++ translations and score with COMET, with resume support. |
| google-translategemma-4b-it/builtin/optimize.py | Orchestrates Olive exports and patches GenAI/processor/tokenizer configs. |
| google-translategemma-4b-it/builtin/user_script.py | Provides PyTorch wrapper modules + IO/dummy-input helpers for Olive export. |
| google-translategemma-4b-it/builtin/cpu_and_mobile/text.json | Olive config for INT4 RTN text decoder export. |
| google-translategemma-4b-it/builtin/cpu_and_mobile/embedding.json | Olive config for embedding/scatter ONNX export. |
| google-translategemma-4b-it/builtin/cpu_and_mobile/vision.json | Olive config for vision encoder ONNX export. |
| google-translategemma-4b-it/builtin/cpu_and_mobile_fp32/text.json | Olive config for FP32 text decoder export. |
| google-translategemma-4b-it/builtin/cpu_and_mobile_fp32/embedding.json | Olive config for FP32 embedding/scatter ONNX export. |
| google-translategemma-4b-it/builtin/cpu_and_mobile_fp32/vision.json | Olive config for FP32 vision encoder ONNX export. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Author
|
@microsoft-github-policy-service agree company="AMD" |
|
@xieofxie / @devang-ml pls review |
tanzeel-amd
force-pushed
the
translate-gemma-4b
branch
from
4d43b33 to
6fae78b
Compare
|
@xieofxie can you please review this? |
xieofxie
reviewed
May 22, 2026
- Introduced benchmark_wmt24pp.py for evaluating translation quality on the WMT24++ dataset using COMET. - Added inference.py for text and image translation capabilities. - Created README.md with setup instructions, usage examples, and model architecture details. - Implemented optimization pipeline in optimize.py for exporting sub-models (text decoder, vision encoder, embedding) with INT4 quantization. - Developed user script in user_script.py for model integration. - Configured export settings in JSON files for different model variants (INT4, AWQ, FP32). - Included test images for demonstration purposes.
- README.md: Remove nonexistent AWQ config references, fix file tree to match actual repo layout (google-translategemma-4b-it/, no data/ dir) - benchmark_wmt24pp.py: Default --hf-model-dir to HF model ID, remove unused stream param and dead new_pairs variable - inference.py: Remove unused numpy import - builtin/user_script.py: Remove unused math, os, glob imports Co-authored-by: Cursor <cursoragent@cursor.com>
Moved README.md, inference.py, benchmark_wmt24pp.py into builtin/ to follow the common recipe file organization pattern. Added info.yml with recipe metadata. Updated default model paths in inference.py and benchmark_wmt24pp.py. Co-authored-by: Cursor <cursoragent@cursor.com>
tanzeel-amd
force-pushed
the
translate-gemma-4b
branch
from
22328c6 to
ada0ad0
Compare
xieofxie
approved these changes
May 25, 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
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.
Adds a complete Olive recipe to export and run google/translategemma-4b-it as a three-submodel VLM pipeline via ONNX Runtime GenAI. TranslateGemma is a Gemma3-based multimodal translation model supporting 55 languages with both text-to-text and image-to-text translation.
What's included