* Combine documentation from all optimum subpackages
* style
* add links
* update workflow
* fix habana section title
* move habana section to make it closer to intel
* add redirects
* remove tflite
* rm exporters-tf
* Update setup.py
* Update setup.py
* Update .github/ISSUE_TEMPLATE/bug-report.yml
* use rm-tflite branch
* fix command registration
* use a model that has safetensors to avoid macos-13 ci failing
* remove some onnx/onnxruntime stuff
* fix
* fix
* test
* test non docker intel doc build
* Add ONNX export support for chinese CLIP
* remove chinese clip normalized config
* remove chinese projection config
* fix
* remove as unused
* remove config
---------
Co-authored-by: Ella Charlaix <[email protected]>
* added test_decoders.py
* fix position ids for single batch and more complete decoder testing for finegrained debugging
* support merging seq2seq models when used as decoders and add more tests
* fix pipe tests
* update phi min transformers version (broken by cache position refactorization)
* remove deprecated bloom modeling
* update opt onnx config to the one with position ids
* remove all complex deprecated modeling
* get_supported_model_type_for_task should only return suooprted model types
* update min transformers
* use transformers like api for use_cache and add can_use_cache and is_merged
* testing
* fix
* fix
* remove unnecessary
* simply qwen3
* docs
* qwen-moe
* model type shenanigans
* fix
* use test models from optimum-internal-hf with proper metadata
* Update optimum/onnxruntime/modeling_decoder.py
Co-authored-by: Ella Charlaix <[email protected]>
* keep supported model types
* optimum model
* fix failing test by forcing export
---------
Co-authored-by: Ella Charlaix <[email protected]>
* Add ONNX export support for D-FINE
* Patch transformers version incompatibility (missing import)
* add min transformers version
* rename
---------
Co-authored-by: Ella Charlaix <[email protected]>
* docs: fixed minor typo in quicktour.mdx
* docs: fixed missing closing quotations mark in onnx/runtime/usage_guides/models.mdx
* docs: removed extra quotation mark at the end in onnxruntime/usage_guides/optimization.mdx
* docs: fixed spelling of NVIDIA in bettertransformer/overview.mdx
* docs: fixed other typos in bettertransformer/overview.mdx
* docs: fixed multiple typos in bettertransformer/tutorials/contribute.mdx
* docs: corrected minor typos and grammar in bettertransformer/tutorials/convert.mdx
* Introduce `DisableCompileContextManager`
* DisableCompileContextManager definition
* Add ONNX export support for modernbert
* Always use `DisableCompileContextManager` during export
* Add modernbert to listed models
* Add modernbert unit tests
* Add support for siglip models
* cleanup
* remove submodule
* Add ONNX export for DinoV2 models
* Use height and width from preprocessor
* formatting
* Remove attention mask from model input
* Add ONNX export support for Hiera models
* Add ONNX export support for SwinV2
* Upgrade Siglip to opset=14
* Add VQA task
* Add ONNX export support for Maskformer
* Add ONNX export support for PVT
* Add ONNX export support for ViTMAE and ViTMSN
* Add siglip unit tests
* Add vit-mae unit tests
* Code formatting
* Add maskformer to list of supported models
* Formatting
* fix typo
* remove vit-mae masked-im task
* remove vit-msn masked-im task
* fix output names for maskformer export
---------
Co-authored-by: Ella Charlaix <[email protected]>
* Enable mpg-str ONNX export
* No longer needed
* Improve model patcher
* Formatting
* `ruff`
* Also support image-to-text task
* Add unit tests
* Add listed support for MGP-STR
* ONNX config for RemBERT added
* added RemBERT to TasksManager
* rembert added to exporters_utils
* RemBERT added to test modelling tasks
* changed rembert model
* added RemBERT to test utils
* Added RemBERT to documentation
* Apply suggestions from code review
---------
Co-authored-by: Ilyas Moutawwakil <[email protected]>
* add phi3 support
* add test
* add phi3 to modeeling test
* replace ckpt to avoid remote code
* fix test
* bump trfrs to fix test
---------
Co-authored-by: Jingya <[email protected]>
Rohan170603