All pull requests

Pull requests

• [ci] Use aks-linux-16-cores-64gb runner for WC tests

  documentationNNCF PTQ
  #4260·AlexanderDokuchaev opened Oct 6, 2026Collaborator·

  ·
  3

• [ONNX] Fix incorrect weight tensor name determination when intermediate nodes exist between the weight and the node

  NNCF ONNX
  #4259·andrey-churkin opened Oct 6, 2026Contributor·

  ·

• Bump the pip group across 15 directories with 1 update

  NNCF OpenVINONNCF PTNNCF PTQpython
  #4258·dependabot[bot] opened Oct 6, 2026Bot·

  ·

• [ci] Add conformance ptq test

  NNCF PTQ
  #4257·AlexanderDokuchaev opened Oct 5, 2026Collaborator·

  ·
  3

• Enable validation on python 3.15

  #4254·AlexanderDokuchaev opened Oct 5, 2026Collaborator·

  ·

• Bump pandas from 2.3.3 to 3.0.6

  python
  #4249·dependabot[bot] opened Oct 5, 2026Bot·

  ·
  

• [Torch] Add the GroupedMatMul operation for data-free weight compression

  NNCF PT
  #4241·anzr299 opened Sep 28, 2026Collaborator·

  ·
  11

• [Common] Make Group Size Default to None

  NNCF OpenVINO
  #4237·anzr299 opened Sep 25, 2026Collaborator·

  ·
  5

• [Common] Decouple Ignored Scope and Introduce Scope Class

  APINNCF Common
  #4236·anzr299 opened Sep 24, 2026Collaborator·

  ·
  6

• [ci] Regenerate reference files

  NNCF CommonNNCF ONNXNNCF OpenVINONNCF PT
  #4232·AlexanderDokuchaev opened Sep 23, 2026Collaborator·

  ·
  3

• Bump onnx to 1.23.0

  documentationNNCF ONNXNNCF OpenVINONNCF PT
  #4229·AlexanderDokuchaev opened Sep 22, 2026Collaborator·

  ·
  5

  

• [Torch][MoE] Support GroupedMM in Torch Backend

  #4209·anzr299 opened Sep 10, 2026Collaborator·

  ·

• [TorchFX] Stop using PT commands and migrate to FX commands

  NNCF PT
  #4183·harshitthek opened Sep 4, 2026·

  ·
  2

• Fix PT2E Mul weight quantization for parameters

  #4173·ricardoasouz opened Aug 15, 2026·

  ·
  5

  

• [Common] Custom Annotation For Weights Compression

  APIdocumentationNNCF CommonNNCF ONNXNNCF OpenVINONNCF PT
  #4171·anzr299 opened Aug 13, 2026Collaborator·

  ·
  30

• [WIP] Add INT2_ASYM weight compression mode

  NNCF OpenVINO
  #4168·Cyberpunk1210 opened Aug 10, 2026·

  ·
  4

  

• Added support of 2-3 bit symmetric mode to LoRA-QAT

  APIdocumentationNNCF OpenVINO
  #4158·andreyanufr opened Jul 30, 2026Collaborator·

  ·
  51

• CVS-191622 [GHA] Docker action for NNCF pipeline

  documentation
  #4156·gkoscins opened Jul 28, 2026Contributor·

  ·
  4

• [FBC] Support models without the batch dimension

  #4149·darshil929 opened Jul 20, 2026Contributor·

  ·
  1

• [Examples] [TorchFX] Make FX Example Prompt Same as OpenVINO Example

  #4127·anzr299 opened Jul 3, 2026Collaborator·

  ·

• Cache statistics in OpenVINO/ONNX Accuracy Restorer

  #4113·andersendsa opened Jun 25, 2026·

  ·
  2

• [Torch] Lora kernels compilation

  #4100·daniil-lyakhov opened Jun 15, 2026Contributor·

  ·
  6

• [GHA] Add Code Coverage workflow

  #4071·mkruszyx opened May 14, 2026·

  ·
  8

• [OpenVINO] calibration_device parameter

  APINNCF ONNXNNCF OpenVINONNCF PTNNCF PTQ
  #4055·daniil-lyakhov opened Apr 28, 2026Contributor·

  ·
  7

• feat: add HQQ data-free weight compression algorithm

  NNCF OpenVINO
  #3981·abhayuvi opened Mar 13, 2026·

  ·
  8