* Fixed Model Optimization Guide and NNCF docs
* Fixed the link to Optimum
* Updated installatin guide
* Changed API description
* Changes quantization documents
* Fixed links in the relevant components
* Fixed API description
* Revised CLI document
* Fixed formatting bugs in the main document
* Fixed formatting bugs in the main document
* Changed the structure. Added Default quantization usage via API
* Fixed E2E CLI example
* Added AccuracyAware usage description
* Revised structure and examples
* Fixed a link to POT intro
* Changed the structure for algorithms
* Fixed links
* Additional fixed of the links
* Revised Ranger documentation
* Some fixes
* Revised Best Practicies
* Fixed descriptions
* Fixed section names
* Changed the workflow one more time
* Additional fixes to the model structure
* Fixed AA usage
* Added DefaultQuantization flow image
* Fixed many issues
* Fixed many issues
* Applied many comments
* Additional fixes
* Fixed examples and provided links to them
* Changed DataLoader Example. Fixed FAQ
* Changed the main README for GitHub
* Fixed E2E CLI example
* Fixed links and code of DataLoader
* Fixed build issues
* Fixed more links
* Fixed one more documentation build issue
* Fixed more links
* Fixed code example
* Add multiple data loaders
* Add audio example
* Minor fixes in the code of sample loaders
* Add descriptions of dataloaders. Changed the behaviour of text loader
* Fixed typos
* Added a new item into the FAQ
* Apply wording corrections
* Update docs/OV_Runtime_UG/supported_plugins/CPU.md
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Fixed comments
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Brushed the general optimization page
* Opt GUIDE, WIP
* perf hints doc placeholder
* WIP
* WIP2
* WIP 3
* added streams and few other details
* fixed titles, misprints etc
* Perf hints
* movin the runtime optimizations intro
* fixed link
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* some details on the FIL and other means when pure inference time is not the only factor
* shuffled according to general->use-case->device-specifics flow, minor brushing
* next iter
* section on optimizing for tput and latency
* couple of links to the features support matrix
* Links, brushing, dedicated subsections for Latency/FIL/Tput
* had to make the link less specific (otherwise docs compilations fails)
* removing the Temp/Should be moved to the Opt Guide
* shuffled the tput/latency/etc info into separated documents. also the following docs moved from the temp into specific feature, general product desc or corresponding plugins
- openvino_docs_IE_DG_Model_caching_overview
- openvino_docs_IE_DG_Int8Inference
- openvino_docs_IE_DG_Bfloat16Inference
- openvino_docs_OV_UG_NoDynamicShapes
* fixed toc for ov_dynamic_shapes.md
* referring the openvino_docs_IE_DG_Bfloat16Inference to avoid docs compilation errors
* fixed main product TOC, removed ref from the second-level items
* reviewers remarks
* reverted the openvino_docs_OV_UG_NoDynamicShapes
* reverting openvino_docs_IE_DG_Bfloat16Inference and openvino_docs_IE_DG_Int8Inference
* "No dynamic shapes" to the "Dynamic shapes" as TOC
* removed duplication
* minor brushing
* Caching to the next level in TOC
* brushing
* more on the perf counters ( for latency and dynamic cases)
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Alexander Kozlov