Release v2.14.1 of NNCF to master

openvinotoolkit · Dec 19, 2024 · 5bfbed5 · 5bfbed5
1 parent 66f63a4
commit 5bfbed5
Show file tree

Hide file tree

Showing 56 changed files with 1,009 additions and 366 deletions.
diff --git a/README.md b/README.md
@@ -394,18 +394,14 @@ A list of notebooks demonstrating OpenVINO conversion and inference together wit
 | [InstructPix2Pix](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/instruct-pix2pix-image-editing)                                                                                                                                                                                                                     |            Post-Training Quantization             | OpenVINO  |                            Image-to-Image                            |
 | [CLIP](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/clip-zero-shot-image-classification)                                                                                                                                                                                                                           |            Post-Training Quantization             | OpenVINO  |                            Image-to-Text                             |
 | [BLIP](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/blip-visual-language-processing)                                                                                                                                                                                                                               |            Post-Training Quantization             | OpenVINO  |                            Image-to-Text                             |
-| [Segmind-VegaRT](https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/stable-diffusion-xl/segmind-vegart.ipynb)                                                                                                                                                                                                            |            Post-Training Quantization             | OpenVINO  |                            Text-to-Image                             |
 | [Latent Consistency Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/latent-consistency-models-image-generation)                                                                                                                                                                                                |            Post-Training Quantization             | OpenVINO  |                            Text-to-Image                             |
-| [Würstchen](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/wuerstchen-image-generation)                                                                                                                                                                                                                              |            Post-Training Quantization             | OpenVINO  |                            Text-to-Image                             |
 | [ControlNet QR Code Monster](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/qrcode-monster)                                                                                                                                                                                                                          |            Post-Training Quantization             | OpenVINO  |                            Text-to-Image                             |
 | [SDXL-turbo](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/sdxl-turbo)                                                                                                                                                                                                                                              |            Post-Training Quantization             | OpenVINO  |                   Text-to-Image,<br>Image-to-Image                   |
-| [ImageBind](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/image-bind)                                                                                                                                                                                                                                               |            Post-Training Quantization             | OpenVINO  |                        Multi-Modal Retrieval                         |
 | [Distil-Whisper](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/distil-whisper-asr)                                                                                                                                                                                                                                  |            Post-Training Quantization             | OpenVINO  |                            Speech-to-Text                            |
 | [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                            |
 | [MMS Speech Recognition](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/mms-massively-multilingual-speech)                                                                                                                                                                                                           |            Post-Training Quantization             | OpenVINO  |                            Speech-to-Text                            |
 | [Grammar Error Correction](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/grammar-correction)                                                                                                                                                                                                                        |            Post-Training Quantization             | OpenVINO  |                       NLP, Grammar Correction                        |
 | [LLM Instruction Following](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-question-answering)                                                                                                                                                                                                                   |                Weight Compression                 | OpenVINO  |                      NLP, Instruction Following                      |
-| [Dolly 2.0](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/dolly-2-instruction-following)                                                                                                                                                                                                                            |                Weight Compression                 | OpenVINO  |                      NLP, Instruction Following                      |
 | [LLM Chat Bots](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot)                                                                                                                                                                                                                                          |                Weight Compression                 | OpenVINO  |                            NLP, Chat Bot                             |
 
 ### Post-Training Quantization Examples

diff --git a/ReleaseNotes.md b/ReleaseNotes.md
@@ -1,5 +1,13 @@
 # Release Notes
 
+## New in Release 2.14.1
+
+Post-training Quantization:
+
+- Bugfixes:
+  - (PyTorch) Fixed the `get_torch_compile_wrapper` function to match with the `torch.compile`.
+  - (OpenVINO) Updated cache statistics functionality to utilize the `safetensors` approach.
+
 ## New in Release 2.14.0
 
 Post-training Quantization:

diff --git a/constraints.txt b/constraints.txt
@@ -1,5 +1,5 @@
 # Openvino
-openvino==2024.5.0
+openvino==2024.6.0
 
 # Pytorch
 torch==2.5.1

diff --git a/docs/Installation.md b/docs/Installation.md
@@ -2,7 +2,7 @@
 
 We suggest to install or use the package in the [Python virtual environment](https://docs.python.org/3/tutorial/venv.html).
 
-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).
+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).
 
 ## As a PyPI package
 
@@ -43,7 +43,8 @@ as well as the supported versions of Python:
 
 | NNCF      | OpenVINO   | PyTorch  | ONNX     | TensorFlow | Python |
 |-----------|------------|----------|----------|------------|--------|
-| `develop` | `2024.5.0` | `2.5.1`  | `1.17.0` | `2.15.1`   | `3.10` |
+| `develop` | `2024.6.0` | `2.5.1`  | `1.17.0` | `2.15.1`   | `3.10` |
+| `2.14.1`  | `2024.6.0` | `2.5.1`  | `1.17.0` | `2.15.1`   | `3.10` |
 | `2.14.0`  | `2024.5.0` | `2.5.1`  | `1.17.0` | `2.15.1`   | `3.10` |
 | `2.13.0`  | `2024.4.0` | `2.4.0`  | `1.16.0` | `2.15.1`   | `3.8`* |
 | `2.12.0`  | `2024.3.0` | `2.3.0`  | `1.16.0` | `2.15.1`   | `3.8`* |

diff --git a/docs/PyPiPublishing.md b/docs/PyPiPublishing.md
@@ -1,5 +1,5 @@
 [![GitHub Release](https://img.shields.io/github/v/release/openvinotoolkit/nncf?color=green)](https://github.com/openvinotoolkit/nncf/releases)
-[![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)
+[![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)
 [![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)
 [![PyPI Downloads](https://static.pepy.tech/badge/nncf)](https://pypi.org/project/nncf/)
 

diff --git a/docs/api/source/conf.py b/docs/api/source/conf.py
@@ -75,7 +75,8 @@ def collect_api_entities() -> APIInfo:
         except Exception as e:
             skipped_modules[modname] = str(e)
 
-    from nncf.common.utils.api_marker import api
+    from nncf.common.utils.api_marker import API_MARKER_ATTR
+    from nncf.common.utils.api_marker import CANONICAL_ALIAS_ATTR
 
     canonical_imports_seen = set()
 
@@ -86,7 +87,7 @@ def collect_api_entities() -> APIInfo:
             if (
                 objects_module == modname
                 and (inspect.isclass(obj) or inspect.isfunction(obj))
-                and hasattr(obj, api.API_MARKER_ATTR)
+                and hasattr(obj, API_MARKER_ATTR)
             ):
                 marked_object_name = obj._nncf_api_marker
                 # Check the actual name of the originally marked object
@@ -95,8 +96,8 @@ def collect_api_entities() -> APIInfo:
                 if marked_object_name != obj.__name__:
                     continue
                 fqn = f"{modname}.{obj_name}"
-                if hasattr(obj, api.CANONICAL_ALIAS_ATTR):
-                    canonical_import_name = getattr(obj, api.CANONICAL_ALIAS_ATTR)
+                if hasattr(obj, CANONICAL_ALIAS_ATTR):
+                    canonical_import_name = getattr(obj, CANONICAL_ALIAS_ATTR)
                     if canonical_import_name in canonical_imports_seen:
                         assert False, f"Duplicate canonical_alias detected: {canonical_import_name}"
                     retval.fqn_vs_canonical_name[fqn] = canonical_import_name
@@ -142,6 +143,8 @@ def collect_api_entities() -> APIInfo:
     "nncf.tensor.functions.numpy_linalg",
     "nncf.tensor.functions.torch_numeric",
     "nncf.tensor.functions.torch_linalg",
+    "nncf.tensor.functions.torch_io",
+    "nncf.tensor.functions.numpy_io",
 ]
 
 with mock(mock_modules):

diff --git a/docs/usage/post_training_compression/weights_compression/Usage.md b/docs/usage/post_training_compression/weights_compression/Usage.md
@@ -218,8 +218,6 @@ compressed_model = compress_weights(
 
 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.
 
-> **NOTE**: Use the `statistics_path` option only in the secure environment to avoid any substitution of the files with statistics.
-
 ### Evaluation results
 
 #### Data-free Mixed-Precision on Lambada OpenAI dataset
@@ -688,5 +686,4 @@ Accuracy/footprint trade-off for `microsoft/Phi-3-mini-4k-instruct`:
 List of notebooks demonstrating OpenVINO conversion and inference together with NNCF weight compression for models from various domains:
 
 - [LLM Instruction Following](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-question-answering)
-- [Dolly 2.0](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/dolly-2-instruction-following)
 - [LLM Chat Bots](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/llm-chatbot)
diff --git a/examples/llm_compression/openvino/tiny_llama_find_hyperparams/requirements.txt b/examples/llm_compression/openvino/tiny_llama_find_hyperparams/requirements.txt
@@ -1,7 +1,7 @@
 datasets
 whowhatbench @ git+https://github.com/andreyanufr/who_what_benchmark.git
 numpy>=1.23.5
-openvino==2024.5
+openvino==2024.6
 optimum-intel[openvino]>=1.13.0
 transformers>=4.35.2
 onnx==1.17.0

diff --git a/examples/llm_compression/openvino/tiny_llama_synthetic_data/requirements.txt b/examples/llm_compression/openvino/tiny_llama_synthetic_data/requirements.txt
@@ -1,7 +1,7 @@
 torch==2.5.1
 datasets==3.0.1
 numpy>=1.23.5
-openvino==2024.5
+openvino==2024.6
 optimum-intel[openvino]>=1.13.0
 transformers>=4.35.2
 onnx==1.17.0

diff --git a/examples/post_training_quantization/onnx/mobilenet_v2/requirements.txt b/examples/post_training_quantization/onnx/mobilenet_v2/requirements.txt
@@ -4,5 +4,5 @@ scikit-learn
 fastdownload
 onnx==1.17.0
 onnxruntime==1.19.2
-openvino==2024.5
+openvino==2024.6
 numpy<2
diff --git a/...es/post_training_quantization/onnx/yolov8_quantize_with_accuracy_control/requirements.txt b/...es/post_training_quantization/onnx/yolov8_quantize_with_accuracy_control/requirements.txt
@@ -1,3 +1,3 @@
 ultralytics==8.3.22
 onnx==1.17.0
-openvino==2024.5
+openvino==2024.6
diff --git a/...ining_quantization/openvino/anomaly_stfpm_quantize_with_accuracy_control/requirements.txt b/...ining_quantization/openvino/anomaly_stfpm_quantize_with_accuracy_control/requirements.txt
@@ -1,4 +1,4 @@
 anomalib==0.6.0
-openvino==2024.5
+openvino==2024.6
 setuptools<=72.1.0
 numpy<2
diff --git a/examples/post_training_quantization/openvino/mobilenet_v2/requirements.txt b/examples/post_training_quantization/openvino/mobilenet_v2/requirements.txt
@@ -2,4 +2,4 @@ torchvision
 tqdm
 scikit-learn
 fastdownload
-openvino==2024.5
+openvino==2024.6
diff --git a/examples/post_training_quantization/openvino/yolov8/requirements.txt b/examples/post_training_quantization/openvino/yolov8/requirements.txt
@@ -1,3 +1,3 @@
 ultralytics==8.3.22
 onnx==1.17.0
-openvino==2024.5
+openvino==2024.6
diff --git a/...ost_training_quantization/openvino/yolov8_quantize_with_accuracy_control/requirements.txt b/...ost_training_quantization/openvino/yolov8_quantize_with_accuracy_control/requirements.txt
@@ -1,3 +1,3 @@
 ultralytics==8.3.22
 onnx==1.17.0
-openvino==2024.5
+openvino==2024.6
diff --git a/examples/post_training_quantization/tensorflow/mobilenet_v2/requirements.txt b/examples/post_training_quantization/tensorflow/mobilenet_v2/requirements.txt
@@ -2,4 +2,4 @@ tensorflow~=2.12.0; python_version < '3.9'
 tensorflow~=2.15.1; python_version >= '3.9'
 tensorflow-datasets
 tqdm
-openvino==2024.5
+openvino==2024.6
diff --git a/examples/post_training_quantization/torch/mobilenet_v2/requirements.txt b/examples/post_training_quantization/torch/mobilenet_v2/requirements.txt
@@ -1,5 +1,5 @@
 fastdownload==0.0.7
-openvino==2024.5
+openvino==2024.6
 scikit-learn
 torch==2.5.1
 torchvision==0.20.1

diff --git a/examples/post_training_quantization/torch/ssd300_vgg16/requirements.txt b/examples/post_training_quantization/torch/ssd300_vgg16/requirements.txt
@@ -1,6 +1,6 @@
 fastdownload==0.0.7
 onnx==1.17.0
-openvino==2024.5
+openvino==2024.6
 pycocotools==2.0.7
 torch==2.5.1
 torchmetrics==1.0.1

diff --git a/examples/post_training_quantization/torch_fx/resnet18/requirements.txt b/examples/post_training_quantization/torch_fx/resnet18/requirements.txt
@@ -1,4 +1,4 @@
 fastdownload==0.0.7
-openvino==2024.5
+openvino==2024.6
 torch==2.5.1
 torchvision==0.20.1
diff --git a/examples/quantization_aware_training/torch/anomalib/requirements.txt b/examples/quantization_aware_training/torch/anomalib/requirements.txt
@@ -1,2 +1,3 @@
 anomalib[core,openvino]==1.0.1
 setuptools<=72.1.0
+matplotlib<3.10.0
diff --git a/examples/quantization_aware_training/torch/resnet18/requirements.txt b/examples/quantization_aware_training/torch/resnet18/requirements.txt
@@ -1,5 +1,5 @@
 fastdownload==0.0.7
-openvino==2024.5
+openvino==2024.6
 torch==2.5.1
 torchvision==0.20.1
 setuptools<=72.1.0