From b951bb1dc68d04ae07c23858c58da94cd979d92c Mon Sep 17 00:00:00 2001 From: Alexander Dokuchaev Date: Wed, 19 Feb 2025 23:15:27 +0200 Subject: [PATCH] remove dead link --- README.md | 2 -- docs/PyPiPublishing.md | 4 ---- nncf/experimental/torch/sparsity/movement/MovementSparsity.md | 4 ---- 3 files changed, 10 deletions(-) diff --git a/README.md b/README.md index 32ee76e4106..00674fb442f 100644 --- a/README.md +++ b/README.md @@ -59,8 +59,6 @@ learning frameworks. - GPU-accelerated layers for faster compressed model fine-tuning. - Distributed training support. - Git patch for prominent third-party repository ([huggingface-transformers](https://github.com/huggingface/transformers)) demonstrating the process of integrating NNCF into custom training pipelines. -- Seamless combination of pruning, sparsity, and quantization algorithms. Please refer to [optimum-intel](https://github.com/huggingface/optimum-intel/tree/main/examples/openvino) for examples of -joint (movement) pruning, quantization, and distillation (JPQD), end-to-end from NNCF optimization to compressed OpenVINO IR. - Exporting PyTorch compressed models to ONNX\* checkpoints and TensorFlow compressed models to SavedModel or Frozen Graph format, ready to use with [OpenVINO™ toolkit](https://docs.openvino.ai). - Support for [Accuracy-Aware model training](./docs/usage/training_time_compression/other_algorithms/Usage.md#accuracy-aware-model-training) pipelines via the [Adaptive Compression Level Training](./docs/accuracy_aware_model_training/AdaptiveCompressionLevelTraining.md) and [Early Exit Training](./docs/accuracy_aware_model_training/EarlyExitTraining.md). diff --git a/docs/PyPiPublishing.md b/docs/PyPiPublishing.md index f91d9701f0e..d0d97d5a070 100644 --- a/docs/PyPiPublishing.md +++ b/docs/PyPiPublishing.md @@ -67,10 +67,6 @@ For more information about NNCF, see: - Git patch for prominent third-party repository ([huggingface-transformers](https://github.com/huggingface/transformers)) demonstrating the process of integrating NNCF into custom training pipelines. -- Seamless combination of pruning, sparsity, and quantization algorithms. Refer - to [optimum-intel](https://github.com/huggingface/optimum-intel/tree/main/examples/openvino) - for examples of joint (movement) pruning, quantization, and distillation - (JPQD), end-to-end from NNCF optimization to compressed OpenVINO IR. - Exporting PyTorch compressed models to ONNX\* checkpoints and TensorFlow compressed models to SavedModel or Frozen Graph format, ready to use with [OpenVINO™ toolkit](https://docs.openvino.ai). diff --git a/nncf/experimental/torch/sparsity/movement/MovementSparsity.md b/nncf/experimental/torch/sparsity/movement/MovementSparsity.md index 800b466827c..f7725c4ea16 100644 --- a/nncf/experimental/torch/sparsity/movement/MovementSparsity.md +++ b/nncf/experimental/torch/sparsity/movement/MovementSparsity.md @@ -43,10 +43,6 @@ This diagram is the sparsity level of BERT-base model over the optimization life Optimized models are compatible with OpenVINO toolchain. Use `compression_controller.export_model("movement_sparsified_model.onnx")` to export model in onnx format. Sparsified parameters in the onnx are in value of zero. Structured sparse structures can be discarded during ONNX translation to OpenVINO IR using [Model Conversion](https://docs.openvino.ai/2025/openvino-workflow/model-preparation/convert-model-to-ir.html) with utilizing [pruning transformation](https://docs.openvino.ai/2025/openvino-workflow/model-optimization-guide/compressing-models-during-training/filter-pruning.html). Corresponding IR is compressed and deployable with [OpenVINO Runtime](https://docs.openvino.ai/2025/openvino-workflow/running-inference.html). To quantify inference performance improvement, both ONNX and IR can be profiled using [Benchmark Tool](https://docs.openvino.ai/2025/get-started/learn-openvino/openvino-samples/benchmark-tool.html). -## Getting Started - -Please refer [optimum-intel](https://github.com/huggingface/optimum-intel/tree/main/examples/openvino) for example pipelines on image classification, question answering, etc. The repository also provides examples of joint pruning, quantization and distillation, end-to-end from NNCF optimization to compressed OpenVINO IR. - ## Known Limitation 1. Movement sparsification only supports `torch.nn.Linear` layers.