feat: add isolated GPTQ-to-OpenVINO export environment under envs/openvino - #65
Merged
aki916f merged 2 commits intoSep 10, 2026
Conversation
…bit export example
…smz/openvino-2026.3
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR adds an isolated OpenVINO 2026.3.1 export environment under
envs/openvino/. It provides a repeatable workflow for converting OneCompGPTQ 4-bit checkpoints to OpenVINO IR and running inference with OpenVINO
GenAI on NPU.
envs/openvino/pyproject.tomlandenvs/openvino/uv.lock): provides pinned conversion dependencies in adedicated
.venv, independently of the main OneComp environment. It usesOpenVINO 2026.3.1 with the matching OpenVINO GenAI and OpenVINO Tokenizers
2026.3.1.0 releases.
envs/openvino/example_export_openvino.py): exportssupported text-generation checkpoints while preserving their existing GPTQ
4-bit weights. It also saves the Hugging Face tokenizer files and the
OpenVINO tokenizer and detokenizer IR required by OpenVINO GenAI.
envs/openvino/openvino_export_utils.py):when
modules_in_block_to_quantizeuses the legacy flatList[str]shape,the exporter copies the checkpoint to a temporary directory and normalizes
the copied configuration to
List[List[str]]before Transformers andOptimum Intel load it. The source checkpoint is not modified.
envs/openvino/README.md): describes environment setup,checkpoint preparation, configuration of
MODEL_PATHandOUT_DIR, exportexecution, NPU inference, and the changes required when adapting the example
to a VLM.
Notes
repository-root
pyproject.tomloruv.lock.TMPDIRcan be set to an existing directory on a filesystem with sufficientcapacity when the default temporary directory is too small.
Validation
uv lock --check --project envs/openvinouv pip check --python envs/openvino/.venv/bin/pythonopenvino_genaiChanges
Environment
OneComp GPTQ 4-bit export example for text-generation models. Flat checkpoint
metadata is normalized in a temporary copy without modifying the source checkpoint.