Skip to content

Conversation

@anzr299
Copy link
Collaborator

@anzr299 anzr299 commented Nov 7, 2025

Changes

The core idea of this change is to first unsqueeze the weights so that it becomes 3D. Even the 2D weights. Then the rest of the algorithm implementation is changed such that it expects the weight shape to be 3D.
Earlier we traversed each group in a weight individually. But now Since we want to find the scales for per-channel as well as per-expert, we traverse by group index as well as batch/expert index (this is just 1 for 2D weights so the behavior is same as before).

Reason for changes

Support AWQ for models with 3D weights such as MoE models.

Related tickets

175789 & 175212

Tests

Current AWQ tests were extended to include the AWQ test models with 3D weights.

Examples Test - 465 - Pass
WC Conformance - 187 - Pass

@github-actions github-actions bot added NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF ONNX Pull requests that updates NNCF ONNX labels Nov 7, 2025
@github-actions github-actions bot removed NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF ONNX Pull requests that updates NNCF ONNX labels Dec 3, 2025
@github-actions github-actions bot added the API Public API-impacting changes label Dec 5, 2025
@github-actions github-actions bot added NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF ONNX Pull requests that updates NNCF ONNX labels Dec 8, 2025
@anzr299 anzr299 marked this pull request as ready for review December 10, 2025 10:28
@anzr299 anzr299 requested a review from a team as a code owner December 10, 2025 10:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

API Public API-impacting changes NNCF ONNX Pull requests that updates NNCF ONNX NNCF OpenVINO Pull requests that updates NNCF OpenVINO

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant