From c6b6acd60efd9a169090ff6452cd9fb0338a702f Mon Sep 17 00:00:00 2001 From: Nikita Malinin Date: Tue, 23 Jul 2024 12:21:22 +0200 Subject: [PATCH 1/7] Update ReleaseNotes.md --- ReleaseNotes.md | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index bc6108d349c..fd0726c445f 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -1,5 +1,53 @@ # Release Notes +## New in Release 2.12.0 + +Post-training Quantization: + +- Breaking changes: + - ... +- General: + - ... +- Features: + - ... +- Fixes: + - ... +- Improvements: + - ... +- Deprecations/Removals: + - ... +- Tutorials: + - ... +- Known issues: + - ... + +Compression-aware training: + +- Breaking changes: + - ... +- General: + - ... +- Features: + - ... +- Fixes: + - ... +- Improvements: + - ... +- Deprecations/Removals: + - ... +- Tutorials: + - ... +- Known issues: + - ... + +Deprecations/Removals: + +- ... + +Requirements: + +- ... + ## New in Release 2.11.0 Post-training Quantization: From 5585997b14652022257e9676868c7139db895059 Mon Sep 17 00:00:00 2001 From: Liubov Talamanova Date: Wed, 24 Jul 2024 10:12:59 +0100 Subject: [PATCH 2/7] Add list of OV notebooks with NNCF to release notes --- ReleaseNotes.md | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index fd0726c445f..560de30645b 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -17,7 +17,16 @@ Post-training Quantization: - Deprecations/Removals: - ... - Tutorials: - - ... + - [Post-Training Optimization of Stable Audio Open Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/stable-audio/stable-audio.ipynb) + - [Post-Training Optimization of Phi3-Vision Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/phi-3-vision/phi-3-vision.ipynb) + - [Post-Training Optimization of MiniCPM-V2 Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/minicpm-v-multimodal-chatbot/minicpm-v-multimodal-chatbot.ipynb) + - [Post-Training Optimization of Jina CLIP Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/jina-clip/jina-clip.ipynb) + - [Post-Training Optimization of Stable Diffusion v3 Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/stable-diffusion-v3/stable-diffusion-v3.ipynb) + - [Post-Training Optimization of HunyuanDIT Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/hunyuan-dit-image-generation/hunyuan-dit-image-generation.ipynb) + - [Post-Training Optimization of DDColor Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/ddcolor-image-colorization/ddcolor-image-colorization.ipynb) + - [Post-Training Optimization of DynamiCrafter Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/dynamicrafter-animating-images/dynamicrafter-animating-images.ipynb) + - [Post-Training Optimization of DepthAnythingV2 Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/depth-anything/depth-anything-v2.ipynb) + - [Post-Training Optimization of Kosmos-2 Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/kosmos2-multimodal-large-language-model/kosmos2-multimodal-large-language-model.ipynb) - Known issues: - ... From 133373e4ba8c743611e55b1da60c866f0dff2257 Mon Sep 17 00:00:00 2001 From: Nikita Savelyev Date: Wed, 24 Jul 2024 13:49:57 +0200 Subject: [PATCH 3/7] Update ReleaseNotes.md Added a note for PR 2803 --- ReleaseNotes.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index 560de30645b..9b888a604fc 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -13,7 +13,7 @@ Post-training Quantization: - Fixes: - ... - Improvements: - - ... + - Reduced the amount of memory required for applying weight compression to OpenVINO models. - Deprecations/Removals: - ... - Tutorials: From ca24f1db5ed855a391b4313acffde5f95bbdcd2f Mon Sep 17 00:00:00 2001 From: Aleksei Kashapov Date: Thu, 25 Jul 2024 18:03:53 +0200 Subject: [PATCH 4/7] Update ReleaseNotes.md --- ReleaseNotes.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index 9b888a604fc..41d752d0dbd 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -11,9 +11,10 @@ Post-training Quantization: - Features: - ... - Fixes: - - ... + - [OpenVINO] Fix ignored_scope for models with IF node. - Improvements: - Reduced the amount of memory required for applying weight compression to OpenVINO models. + - Improved ignored_scope logging. - Deprecations/Removals: - ... - Tutorials: From 140c1e839cc44a5c8732477a07090f801c2e222b Mon Sep 17 00:00:00 2001 From: Liubov Talamanova Date: Fri, 26 Jul 2024 09:45:43 +0100 Subject: [PATCH 5/7] Add changes from PR#2434 --- ReleaseNotes.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index 41d752d0dbd..d006b622ebd 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -7,7 +7,7 @@ Post-training Quantization: - Breaking changes: - ... - General: - - ... + - (Common): Changed the representation of symmetrically quantized weights from an unsigned integer with a fixed zero-point to a signed data type without zero-point in the weights compression algorithm. - Features: - ... - Fixes: From 92373fa805d24a0d99dd4e9ffdf787df52ad2bbf Mon Sep 17 00:00:00 2001 From: Nikita Malinin Date: Fri, 26 Jul 2024 16:29:27 +0200 Subject: [PATCH 6/7] Update release notes --- ReleaseNotes.md | 48 ++++++++++++++++-------------------------------- 1 file changed, 16 insertions(+), 32 deletions(-) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index d006b622ebd..3205aeff8c3 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -4,19 +4,22 @@ Post-training Quantization: -- Breaking changes: - - ... -- General: - - (Common): Changed the representation of symmetrically quantized weights from an unsigned integer with a fixed zero-point to a signed data type without zero-point in the weights compression algorithm. - Features: - - ... + - (OpenVINO, PyTorch, ONNX) Excluded comparison operators from the quantization scope for `nncf.ModelType.TRANSFORMER`. + - (OpenVINO, PyTorch) Changed the representation of symmetrically quantized weights from an unsigned integer with a fixed zero-point to a signed data type without a zero-point in the `nncf.compress_weights()` method. + - (OpenVINO) Extended patterns support of the AWQ algorithm as part of `nncf.compress_weights()`. This allows apply AWQ for the wider scope of the models. + - (OpenVINO) Introduced `nncf.CompressWeightsMode.E2M1` as the new precision for the `mode` option of `nncf.compress_weights()`. + - (OpenVINO) Added support for models with BF16 precision in the `nncf.quantize()` method. + - (PyTorch) Added quantization support for the `torch.addmm`. + - (PyTorch) Added quantization support for the `torch.nn.functional.scaled_dot_product_attention`. - Fixes: - - [OpenVINO] Fix ignored_scope for models with IF node. + - (OpenVINO, PyTorch, ONNX) Fixed Fast-/BiasCorrection algorithms with correct support of transposed MatMul layers. + - (OpenVINO) Fixed `nncf.IgnoredScope()` functionality for models with If operation. + - (OpenVINO) Fixed patterns with PReLU operations. + - Fixed runtime error while importing NNCF without Matplotlib package. - Improvements: - - Reduced the amount of memory required for applying weight compression to OpenVINO models. - - Improved ignored_scope logging. -- Deprecations/Removals: - - ... + - Reduced the amount of memory required for applying `nncf.compress_weights()` to OpenVINO models. + - Improved logging in case of the not empty `nncf.IgnoredScope()`. - Tutorials: - [Post-Training Optimization of Stable Audio Open Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/stable-audio/stable-audio.ipynb) - [Post-Training Optimization of Phi3-Vision Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/phi-3-vision/phi-3-vision.ipynb) @@ -28,35 +31,16 @@ Post-training Quantization: - [Post-Training Optimization of DynamiCrafter Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/dynamicrafter-animating-images/dynamicrafter-animating-images.ipynb) - [Post-Training Optimization of DepthAnythingV2 Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/depth-anything/depth-anything-v2.ipynb) - [Post-Training Optimization of Kosmos-2 Model](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/kosmos2-multimodal-large-language-model/kosmos2-multimodal-large-language-model.ipynb) -- Known issues: - - ... Compression-aware training: -- Breaking changes: - - ... -- General: - - ... -- Features: - - ... - Fixes: - - ... -- Improvements: - - ... -- Deprecations/Removals: - - ... -- Tutorials: - - ... -- Known issues: - - ... - -Deprecations/Removals: - -- ... + - (PyTorch) Fixed issue with wrapping for operator without patched state. Requirements: -- ... +- Updated Tensorflow (2.15) version. This version requires Python 3.9-3.11. +- Added NumPy 2.0 support. ## New in Release 2.11.0 From c3633cce043fe39b6e15377d40ad3f7d86d9d28c Mon Sep 17 00:00:00 2001 From: Nikita Malinin Date: Mon, 29 Jul 2024 12:56:57 +0200 Subject: [PATCH 7/7] Update ReleaseNotes.md Co-authored-by: Alexander Kozlov --- ReleaseNotes.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ReleaseNotes.md b/ReleaseNotes.md index 3205aeff8c3..b43c17627de 100644 --- a/ReleaseNotes.md +++ b/ReleaseNotes.md @@ -8,7 +8,7 @@ Post-training Quantization: - (OpenVINO, PyTorch, ONNX) Excluded comparison operators from the quantization scope for `nncf.ModelType.TRANSFORMER`. - (OpenVINO, PyTorch) Changed the representation of symmetrically quantized weights from an unsigned integer with a fixed zero-point to a signed data type without a zero-point in the `nncf.compress_weights()` method. - (OpenVINO) Extended patterns support of the AWQ algorithm as part of `nncf.compress_weights()`. This allows apply AWQ for the wider scope of the models. - - (OpenVINO) Introduced `nncf.CompressWeightsMode.E2M1` as the new precision for the `mode` option of `nncf.compress_weights()`. + - (OpenVINO) Introduced `nncf.CompressWeightsMode.E2M1` `mode` option of `nncf.compress_weights()` as the new MXFP4 precision (Experimental). - (OpenVINO) Added support for models with BF16 precision in the `nncf.quantize()` method. - (PyTorch) Added quantization support for the `torch.addmm`. - (PyTorch) Added quantization support for the `torch.nn.functional.scaled_dot_product_attention`.