Skip to content

Commit 5bfbed5

Browse files
alexsu52alexsu52
committed
Release v2.14.1 of NNCF to master
1 parent 66f63a4 commit 5bfbed5

File tree

56 files changed

+1009
-366
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

56 files changed

+1009
-366
lines changed

‎README.md

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -394,18 +394,14 @@ A list of notebooks demonstrating OpenVINO conversion and inference together wit
394394
| [InstructPix2Pix](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/instruct-pix2pix-image-editing) | Post-Training Quantization | OpenVINO | Image-to-Image |
395395
| [CLIP](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/clip-zero-shot-image-classification) | Post-Training Quantization | OpenVINO | Image-to-Text |
396396
| [BLIP](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/blip-visual-language-processing) | Post-Training Quantization | OpenVINO | Image-to-Text |
397-
| [Segmind-VegaRT](https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/stable-diffusion-xl/segmind-vegart.ipynb) | Post-Training Quantization | OpenVINO | Text-to-Image |
398397
| [Latent Consistency Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/latent-consistency-models-image-generation) | Post-Training Quantization | OpenVINO | Text-to-Image |
399-
| [Würstchen](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/wuerstchen-image-generation) | Post-Training Quantization | OpenVINO | Text-to-Image |
400398
| [ControlNet QR Code Monster](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/qrcode-monster) | Post-Training Quantization | OpenVINO | Text-to-Image |
401399
| [SDXL-turbo](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/sdxl-turbo) | Post-Training Quantization | OpenVINO | Text-to-Image,<br>Image-to-Image |
402-
| [ImageBind](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/image-bind) | Post-Training Quantization | OpenVINO | Multi-Modal Retrieval |
403400
| [Distil-Whisper](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/distil-whisper-asr) | Post-Training Quantization | OpenVINO | Speech-to-Text |
404401
| [Whisper](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/whisper-subtitles-generation)<br>[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/whisper-subtitles-generation/whisper-convert.ipynb) | Post-Training Quantization | OpenVINO | Speech-to-Text |
405402
| [MMS Speech Recognition](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/mms-massively-multilingual-speech) | Post-Training Quantization | OpenVINO | Speech-to-Text |
406403
| [Grammar Error Correction](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/grammar-correction) | Post-Training Quantization | OpenVINO | NLP, Grammar Correction |
407404
| [LLM Instruction Following](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-question-answering) | Weight Compression | OpenVINO | NLP, Instruction Following |
408-
| [Dolly 2.0](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/dolly-2-instruction-following) | Weight Compression | OpenVINO | NLP, Instruction Following |
409405
| [LLM Chat Bots](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot) | Weight Compression | OpenVINO | NLP, Chat Bot |
410406

411407
### Post-Training Quantization Examples

‎ReleaseNotes.md

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,13 @@
11
# Release Notes
22

3+
## New in Release 2.14.1
4+
5+
Post-training Quantization:
6+
7+
- Bugfixes:
8+
- (PyTorch) Fixed the `get_torch_compile_wrapper` function to match with the `torch.compile`.
9+
- (OpenVINO) Updated cache statistics functionality to utilize the `safetensors` approach.
10+
311
## New in Release 2.14.0
412

513
Post-training Quantization:

‎constraints.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
# Openvino
2-
openvino==2024.5.0
2+
openvino==2024.6.0
33

44
# Pytorch
55
torch==2.5.1

‎docs/Installation.md

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22

33
We suggest to install or use the package in the [Python virtual environment](https://docs.python.org/3/tutorial/venv.html).
44

5-
If you want to optimize a model from PyTorch, install PyTorch by following [PyTorch installation guide](https://pytorch.org/get-started/locally/#start-locally). For other backend follow: [TensorFlow installation guide](https://www.tensorflow.org/install/), [ONNX installation guide](https://onnxruntime.ai/docs/install/), [OpenVINO installation guide](https://docs.openvino.ai/latest/openvino_docs_install_guides_overview.html).
5+
If you want to optimize a model from PyTorch, install PyTorch by following [PyTorch installation guide](https://pytorch.org/get-started/locally/#start-locally). For other backend follow: [TensorFlow installation guide](https://www.tensorflow.org/install/), [ONNX installation guide](https://onnxruntime.ai/docs/install/), [OpenVINO installation guide](https://docs.openvino.ai/2024/get-started/install-openvino.html).
66

77
## As a PyPI package
88

@@ -43,7 +43,8 @@ as well as the supported versions of Python:
4343

4444
| NNCF | OpenVINO | PyTorch | ONNX | TensorFlow | Python |
4545
|-----------|------------|----------|----------|------------|--------|
46-
| `develop` | `2024.5.0` | `2.5.1` | `1.17.0` | `2.15.1` | `3.10` |
46+
| `develop` | `2024.6.0` | `2.5.1` | `1.17.0` | `2.15.1` | `3.10` |
47+
| `2.14.1` | `2024.6.0` | `2.5.1` | `1.17.0` | `2.15.1` | `3.10` |
4748
| `2.14.0` | `2024.5.0` | `2.5.1` | `1.17.0` | `2.15.1` | `3.10` |
4849
| `2.13.0` | `2024.4.0` | `2.4.0` | `1.16.0` | `2.15.1` | `3.8`* |
4950
| `2.12.0` | `2024.3.0` | `2.3.0` | `1.16.0` | `2.15.1` | `3.8`* |

‎docs/PyPiPublishing.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
[![GitHub Release](https://img.shields.io/github/v/release/openvinotoolkit/nncf?color=green)](https://github.com/openvinotoolkit/nncf/releases)
2-
[![Website](https://img.shields.io/website?up_color=blue&up_message=docs&url=https%3A%2F%2Fdocs.openvino.ai%2Flatest%2Fopenvino_docs_model_optimization_guide.html)](https://docs.openvino.ai/nncf)
2+
[![Website](https://img.shields.io/website?up_color=blue&up_message=docs&url=https%3A%2F%2Fdocs.openvino.ai%2Fnncf)](https://docs.openvino.ai/nncf)
33
[![Apache License Version 2.0](https://img.shields.io/badge/license-Apache_2.0-green.svg)](https://github.com/openvinotoolkit/nncf?tab=Apache-2.0-1-ov-file#readme)
44
[![PyPI Downloads](https://static.pepy.tech/badge/nncf)](https://pypi.org/project/nncf/)
55

‎docs/api/source/conf.py

Lines changed: 7 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -75,7 +75,8 @@ def collect_api_entities() -> APIInfo:
7575
except Exception as e:
7676
skipped_modules[modname] = str(e)
7777

78-
from nncf.common.utils.api_marker import api
78+
from nncf.common.utils.api_marker import API_MARKER_ATTR
79+
from nncf.common.utils.api_marker import CANONICAL_ALIAS_ATTR
7980

8081
canonical_imports_seen = set()
8182

@@ -86,7 +87,7 @@ def collect_api_entities() -> APIInfo:
8687
if (
8788
objects_module == modname
8889
and (inspect.isclass(obj) or inspect.isfunction(obj))
89-
and hasattr(obj, api.API_MARKER_ATTR)
90+
and hasattr(obj, API_MARKER_ATTR)
9091
):
9192
marked_object_name = obj._nncf_api_marker
9293
# Check the actual name of the originally marked object
@@ -95,8 +96,8 @@ def collect_api_entities() -> APIInfo:
9596
if marked_object_name != obj.__name__:
9697
continue
9798
fqn = f"{modname}.{obj_name}"
98-
if hasattr(obj, api.CANONICAL_ALIAS_ATTR):
99-
canonical_import_name = getattr(obj, api.CANONICAL_ALIAS_ATTR)
99+
if hasattr(obj, CANONICAL_ALIAS_ATTR):
100+
canonical_import_name = getattr(obj, CANONICAL_ALIAS_ATTR)
100101
if canonical_import_name in canonical_imports_seen:
101102
assert False, f"Duplicate canonical_alias detected: {canonical_import_name}"
102103
retval.fqn_vs_canonical_name[fqn] = canonical_import_name
@@ -142,6 +143,8 @@ def collect_api_entities() -> APIInfo:
142143
"nncf.tensor.functions.numpy_linalg",
143144
"nncf.tensor.functions.torch_numeric",
144145
"nncf.tensor.functions.torch_linalg",
146+
"nncf.tensor.functions.torch_io",
147+
"nncf.tensor.functions.numpy_io",
145148
]
146149

147150
with mock(mock_modules):

‎docs/usage/post_training_compression/weights_compression/Usage.md

Lines changed: 0 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -218,8 +218,6 @@ compressed_model = compress_weights(
218218

219219
When `statistics_path` is provided, the system first checks if the specified path exists. If it does, the statistics are loaded from this path. If the path does not exist, the statistics are computed and saved to this path for future use.
220220

221-
> **NOTE**: Use the `statistics_path` option only in the secure environment to avoid any substitution of the files with statistics.
222-
223221
### Evaluation results
224222

225223
#### Data-free Mixed-Precision on Lambada OpenAI dataset
@@ -688,5 +686,4 @@ Accuracy/footprint trade-off for `microsoft/Phi-3-mini-4k-instruct`:
688686
List of notebooks demonstrating OpenVINO conversion and inference together with NNCF weight compression for models from various domains:
689687

690688
- [LLM Instruction Following](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-question-answering)
691-
- [Dolly 2.0](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/dolly-2-instruction-following)
692689
- [LLM Chat Bots](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot)

‎examples/llm_compression/openvino/tiny_llama_find_hyperparams/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
datasets
22
whowhatbench @ git+https://github.com/andreyanufr/who_what_benchmark.git
33
numpy>=1.23.5
4-
openvino==2024.5
4+
openvino==2024.6
55
optimum-intel[openvino]>=1.13.0
66
transformers>=4.35.2
77
onnx==1.17.0

‎examples/llm_compression/openvino/tiny_llama_synthetic_data/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
torch==2.5.1
22
datasets==3.0.1
33
numpy>=1.23.5
4-
openvino==2024.5
4+
openvino==2024.6
55
optimum-intel[openvino]>=1.13.0
66
transformers>=4.35.2
77
onnx==1.17.0

‎examples/post_training_quantization/onnx/mobilenet_v2/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,5 +4,5 @@ scikit-learn
44
fastdownload
55
onnx==1.17.0
66
onnxruntime==1.19.2
7-
openvino==2024.5
7+
openvino==2024.6
88
numpy<2

‎examples/post_training_quantization/onnx/yolov8_quantize_with_accuracy_control/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
ultralytics==8.3.22
22
onnx==1.17.0
3-
openvino==2024.5
3+
openvino==2024.6

‎examples/post_training_quantization/openvino/anomaly_stfpm_quantize_with_accuracy_control/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
anomalib==0.6.0
2-
openvino==2024.5
2+
openvino==2024.6
33
setuptools<=72.1.0
44
numpy<2

‎examples/post_training_quantization/openvino/mobilenet_v2/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,4 +2,4 @@ torchvision
22
tqdm
33
scikit-learn
44
fastdownload
5-
openvino==2024.5
5+
openvino==2024.6

‎examples/post_training_quantization/openvino/yolov8/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
ultralytics==8.3.22
22
onnx==1.17.0
3-
openvino==2024.5
3+
openvino==2024.6

‎examples/post_training_quantization/openvino/yolov8_quantize_with_accuracy_control/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
ultralytics==8.3.22
22
onnx==1.17.0
3-
openvino==2024.5
3+
openvino==2024.6

‎examples/post_training_quantization/tensorflow/mobilenet_v2/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,4 +2,4 @@ tensorflow~=2.12.0; python_version < '3.9'
22
tensorflow~=2.15.1; python_version >= '3.9'
33
tensorflow-datasets
44
tqdm
5-
openvino==2024.5
5+
openvino==2024.6

‎examples/post_training_quantization/torch/mobilenet_v2/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
fastdownload==0.0.7
2-
openvino==2024.5
2+
openvino==2024.6
33
scikit-learn
44
torch==2.5.1
55
torchvision==0.20.1

‎examples/post_training_quantization/torch/ssd300_vgg16/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
fastdownload==0.0.7
22
onnx==1.17.0
3-
openvino==2024.5
3+
openvino==2024.6
44
pycocotools==2.0.7
55
torch==2.5.1
66
torchmetrics==1.0.1

‎examples/post_training_quantization/torch_fx/resnet18/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
fastdownload==0.0.7
2-
openvino==2024.5
2+
openvino==2024.6
33
torch==2.5.1
44
torchvision==0.20.1

‎examples/quantization_aware_training/torch/anomalib/requirements.txt

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,2 +1,3 @@
11
anomalib[core,openvino]==1.0.1
22
setuptools<=72.1.0
3+
matplotlib<3.10.0

‎examples/quantization_aware_training/torch/resnet18/requirements.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
fastdownload==0.0.7
2-
openvino==2024.5
2+
openvino==2024.6
33
torch==2.5.1
44
torchvision==0.20.1
55
setuptools<=72.1.0

0 commit comments

Comments
 (0)