Add genie_overrides to QairtEncapsulation for GenAIConfig customization#2469
Open
qti-kromero wants to merge 29 commits into
Open
Add genie_overrides to QairtEncapsulation for GenAIConfig customization#2469qti-kromero wants to merge 29 commits into
qti-kromero wants to merge 29 commits into
Conversation
Introduce a genie_overrides PassConfigParam that deep-merges user-supplied fields into the GenAIConfig before LLMContainer.export() bakes them into the Genie DLC. This allows callers to override any GenAIConfig field (engine config, positional encoding, etc.) without modifying QairtGenAIBuilder or QairtPipelinePass. Nested dicts are merged recursively so only the specified keys are changed; all other values set by the upstream builder pass are preserved.
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
…ensions customization Adds a backend_extensions_override PassConfigParam that is deep-merged into the LLMContainer's existing _backend_extensions_config before the Genie DLC is produced. Uses the raw JSON key names (hyphens) as they appear in backend_extensions.json. Nested dicts are merged recursively so only specified keys are overridden; all other defaults set by the builder are preserved. If the container has no existing backend extensions config, the override becomes the entire config. Includes 4 tests covering default config presence, merge into existing config, merge from empty, and no-op when override is None. Also drops one fragile identity assertion from the existing genie_overrides test.
…ion compatibility
…apsulation
Aligns with qairt-dev's rename of HTPExecutionConfig → HTPEngineConfig wrapped
in EngineConfig (AISW-184594). The param now accepts a nested dict:
{"n_threads": 0, "htp": {"cpu_mask": "0xe0", "poll": false, ...}}
Top-level keys map to EngineConfig, "htp" sub-dict maps to HTPEngineConfig.
…key deletion - Lists of dicts are merged element-wise by index, allowing recipe overrides to target nested list entries (e.g. context[0], devices[0]) without replacing the entire list - A None override value deletes the corresponding key from the result, enabling removal of builder-generated keys (e.g. "graphs": null)
…ain bug - encapsulation.py: add # pylint: disable=protected-access on _gen_ai_config and _backend_extensions_config accesses - test_encapsulation.py: rename htp_execution_overrides → engine_config_overrides throughout; fix docstring capitalization; fix pre-existing test_encapsulation_ genie_overrides_applied failure caused by mock._gen_ai_config being replaced after model_validate() — capture original mock before running the pass
Move _make_minimal_onnx and a mock_container fixture into conftest.py, replace inline mock_save_func/save patches and dead mock_helper.make_* stubs across all tests, parametrize the _default_config and missing-required-file assertions, drop the redundant valid-version test, and add coverage for EPContext node output, QAIRT_LOG_LEVEL env wiring, and sequence_lengths plumbing into create_genai_config.
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
This PR extends the QAIRT encapsulation pass to support deep-merged override configs (GenAIConfig, backend extensions, and engine config), and refactors/expands the test suite to validate these behaviors.
Changes:
- Added
_deep_mergeutility and new pass config params:genie_overrides,backend_extensions_overrides,engine_config_overrides. - Updated encapsulation execution to apply overrides and to optionally pass
engine_configtoLLMContainer.export()when supported. - Refactored tests to use shared fixtures and added new unit/integration tests for merge/override behavior.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.
| File | Description |
|---|---|
olive/passes/qairt/encapsulation.py |
Adds deep-merge + override plumbing and conditional engine_config export support. |
test/passes/qairt/conftest.py |
Introduces shared ONNX writer helper and a reusable mocked container fixture. |
test/passes/qairt/test_encapsulation.py |
Refactors existing tests and adds coverage for overrides, deep merge, env var, and EPContext node validation. |
Comment on lines
+23
to
+26
| input_tensor = onnx.helper.make_tensor_value_info("input_ids", TensorProto.INT32, ["batch_size", "sequence_length"]) | ||
| output_tensor = onnx.helper.make_tensor_value_info( | ||
| "logits", TensorProto.FLOAT, ["batch_size", 1, "sequence_length"] | ||
| ) |
| MAX_GENIE_CONTEXT_LENGTH = 4096 | ||
|
|
||
|
|
||
| def _deep_merge(base: dict, overrides: dict) -> dict: |
| elements are appended. A ``None`` override value deletes the key from | ||
| the result. The returned dict shares no references with *base*. | ||
| """ | ||
| result = copy.deepcopy(base) |
Comment on lines
+42
to
+43
| elif k in result and isinstance(result[k], dict) and isinstance(v, dict): | ||
| result[k] = _deep_merge(result[k], v) |
Comment on lines
+155
to
+156
| export_kwargs = {"export_format": qairt.ExportFormat.LM_EXECUTOR} | ||
| if config.engine_config_overrides: |
Comment on lines
+165
to
+169
| overrides = dict(config.engine_config_overrides) | ||
| htp_overrides = overrides.pop("htp", None) | ||
| htp_cfg = qairt_genai.HTPEngineConfig(**(htp_overrides or {})) if htp_overrides is not None else None | ||
| engine_cfg = qairt_genai.EngineConfig(**overrides, htp=htp_cfg) | ||
| export_kwargs["engine_config"] = engine_cfg |
|
|
||
|
|
||
| def test_encapsulation_successful_execution(tmp_path, mock_qairt_model, mock_qairt_modules): | ||
| from test.passes.qairt.utils import make_minimal_onnx as _make_minimal_onnx |
Contributor
Author
|
@xiaoyu-work @xieofxie @jambayk requesting human reviewer, copilot is wonking out and making circular suggestions |
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.
Introduce a
genie_overridesPassConfigParam that deep-merges user-supplied fields into the GenAIConfig beforeLLMContainer.export()bakes them into the Genie DLC. This allows callers to override any GenAIConfig field (engine config, positional encoding, etc.) without modifyingQairtGenAIBuilderorQairtPipelinePass.Nested dicts are merged recursively so only the specified keys are changed; all other values set by the upstream builder pass are preserved.
Describe your changes
Add a
genie_overridesparameter toQairtEncapsulation. When provided, the value is deep-merged into theGenAIConfigdict just beforeLLMContainer.export()is called. The merge is recursive: nested dicts are merged key-by-key so callers only need to specify the fields they want to change. A helper_deep_mergeutility handles the recursion and is unit-tested directly. Integration tests cover round-trip behavior with nested overrides and verify that unrelated config fields are left untouched.Checklist before requesting a review
Add unit tests for this change.
Make sure all tests can pass.
Update documents if necessary.
Lint and apply fixes to your code by running
lintrunner -aIs this a user-facing change? If yes, give a description of this change to be included in the release notes.
Release note:
QairtEncapsulationnow acceptsgenie_overrides,backend_extensions_overrides, andengine_config_overridesparameters that allow users to override the behavior of underlying Genie components when building Genie DLCs.(Optional) Issue link
N/A