Add QDQ scale propagation pass #713
Open
+1,499
−512
Conversation
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
javier-intel
force-pushed
the
jemartin/scale_propagation
branch
from
3d0ca12 to
4cb9374
Compare
| } else if (session_context_.device_type.find("GPU") != std::string::npos) { | ||
| // Create a copy of the model | ||
| std::unique_ptr<onnxruntime::Model> model; | ||
| Status status = qdq_scales_fix::Transform(subgraph, logger, model); |
There was a problem hiding this comment.
Is this pass happening even for non quantized models?
* Use infer instead of start async/wait * Introduce OvExeceptionBoundary for exception handling * unbound infer request pool * Fix dynamically sized i/o * Rename onnx->ort + remove unused parameter shape functions * fix linux build issue + review dog comments * more linux build fixes + copilot feedback * disable ReduceSum_noop_axes_input_initializer_opset_18 * review feedback + last minute touch ups * slightly more scalable llm handling * Simplify dynamic shape checks * add missing staged changes * Remove references to IO_BUFFER_ENABLED * Minor tweaks to InferRequestPool * remove unused mem_info * Move ParameterShape and ParameterInfo out of ov_interface --------- Co-authored-by: MayureshV1 <47039074+MayureshV1@users.noreply.github.com>
* feat: Enable EpContext OVIR Encapsulation * fix: refactor EpCtx OVIR parsing logic to use ep.context_file_path * fix: Fix logic for parsing model_file_path * fix: enable EPCtx OVIR encapsulation compiled blob caching * fix: fix merge conflicts * fix: fix bugs
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Outdated suggestions cannot be applied.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.
Description
Adding pass to propagate scale values with a magnitude above a certain threshold to avoid numerical overflows.
Motivation and Context
Improve precision on certain networks