-
Notifications
You must be signed in to change notification settings - Fork 259
Pull requests: openvinotoolkit/nncf
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Disable support of python 3.9
documentation
Improvements or additions to documentation
NNCF ONNX
Pull requests that updates NNCF ONNX
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
NNCF PT
Pull requests that updates NNCF PyTorch
NNCF TF
Pull requests that updates NNCF TensorFlow
#3674
opened Oct 1, 2025 by
AlexanderDokuchaev
Loading…
Move Public API-impacting changes
is_weight_compression_needed
function to common
API
#3669
opened Sep 25, 2025 by
aobolensk
Loading…
Enable INT16 quantization in HW configs
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
#3666
opened Sep 25, 2025 by
ljaljushkin
Loading…
[OpenVINO][WC] E2M1 -> MXFP4 and MXFP8_E4M3 weights compression support
API
Public API-impacting changes
documentation
Improvements or additions to documentation
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
#3664
opened Sep 22, 2025 by
daniil-lyakhov
Loading…
[ONNX] Compress quantize weights transformation
NNCF ONNX
Pull requests that updates NNCF ONNX
NNCF PTQ
Pull requests that updates NNCF PTQ
#3662
opened Sep 19, 2025 by
andrey-churkin
Loading…
[ONNX] Add MatMul for FBC/BC
NNCF PTQ
Pull requests that updates NNCF PTQ
#3657
opened Sep 11, 2025 by
andrey-churkin
•
Draft
Don't use RawReducer for activation shape collection in Fast Bias Correction
NNCF Common
Pull request that updates NNCF Common
#3642
opened Aug 28, 2025 by
nikita-savelyevv
Loading…
Bump transformers 4.53.0
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
NNCF PT
Pull requests that updates NNCF PyTorch
NNCF PTQ
Pull requests that updates NNCF PTQ
#3618
opened Aug 12, 2025 by
AlexanderDokuchaev
•
Draft
[TorchFX] Use torchao for quantize_pt2e API when possible
API
Public API-impacting changes
#3588
opened Jul 21, 2025 by
daniil-lyakhov
Loading…
[OV] Optimized compression to f4e2m1 data type
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
#3550
opened Jun 18, 2025 by
nikita-savelyevv
•
Draft
Tensor stats migration
experimental
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
NNCF PT
Pull requests that updates NNCF PyTorch
NNCF PTQ
Pull requests that updates NNCF PTQ
NNCF TF
Pull requests that updates NNCF TensorFlow
#3440
opened Apr 17, 2025 by
darshil929
•
Draft
[FX] Support weight quantization for operations where Pull requests that updates NNCF PTQ
weight_port_id
!= 1
NNCF PTQ
#3334
opened Mar 8, 2025 by
siddhant-0707
Loading…
Use imagenet dataset from hf in conformance tests
documentation
Improvements or additions to documentation
NNCF PTQ
Pull requests that updates NNCF PTQ
#3323
opened Mar 3, 2025 by
AlexanderDokuchaev
•
Draft
Add kwargs to quantize calls
API
Public API-impacting changes
NNCF PTQ
Pull requests that updates NNCF PTQ
#3317
opened Feb 27, 2025 by
nikita-savelyevv
•
Draft
Support transposed input for data-aware Weights Compression
NNCF ONNX
Pull requests that updates NNCF ONNX
NNCF OpenVINO
Pull requests that updates NNCF OpenVINO
NNCF PT
Pull requests that updates NNCF PyTorch
NNCF PTQ
Pull requests that updates NNCF PTQ
#3296
opened Feb 19, 2025 by
rk119
Loading…
llm weight compression tool
documentation
Improvements or additions to documentation
#3290
opened Feb 18, 2025 by
andrey-churkin
•
Draft
[Torch FX] Map Namespace Names to Metatype
experimental
NNCF PT
Pull requests that updates NNCF PyTorch
NNCF PTQ
Pull requests that updates NNCF PTQ
#3237
opened Feb 3, 2025 by
anzr299
Loading…
[WIP][Conformance] Ultralytics yolov8n and yolo11n
NNCF PTQ
Pull requests that updates NNCF PTQ
#3116
opened Nov 26, 2024 by
daniil-lyakhov
•
Draft
Activation Sparsity OV backend
experimental
NNCF PT
Pull requests that updates NNCF PyTorch
#2924
opened Aug 28, 2024 by
nikita-savelyevv
•
Draft
[DRAFT]: Add FracBits experimental feature
documentation
Improvements or additions to documentation
experimental
NNCF Common
Pull request that updates NNCF Common
NNCF PT
Pull requests that updates NNCF PyTorch
ProTip!
Filter pull requests by the default branch with base:develop.