* Bump aiohttp from 3.9.0 to 3.9.2 to resolve security issues
* update url
* remove aiohttp version from requirements.txt
* revert aiohttp to 3.9.0
* trigger tests
* revert
* Update README in LLM GPU Examples
* Update reference of Intel GPU
* add cpu_embedding=True in comment
* small fixes
* update GPU/README.md and add explanation for cpu_embedding=True
* address comments
* fix small typos
* add backtick for cpu_embedding=True
* remove extra backtick in the doc
* add period mark
* update readme
* Improve runtime configuration for windows
* Add python 310/311 supports for wheel downloading
* Add troubleshooting for windows gpu
* Remove manually import ipex due to auto importer
* Add info regarding cpu_embedding=True on iGPU
* More info for Windows users
* Small updates to API docs
* Python style fix
* Remove tip for loading from saved optimize_model for now
* Updated based on comments
* Update win info for multi-intel gpus selection
* Small fix
* Small fix
* Update default xpu to ipex 2.1
* Update related install ut support correspondingly
* Add arc ut tests for both ipex 2.0 and 2.1
* Small fix
* Diable ipex 2.1 test for now as oneapi 2024.0 has not beed installed on the test machine
* Update document for default PyTorch 2.1
* Small fix
* Small fix
* Small doc fixes
* Small fixes
* harness: run llama2-7b
* harness: run llama2-7b
* harness: run llama2-7b
* harness: run llama2-7b
* edit-gpu-doc
* fix some format problem
* fix spelling problems
* fix evaluation yml
* delete redundant space
* fix some problems
* address comments
* change link
* Add arc demo in main readme
* Small style fix
* Realize using table
* Update based on comments
* Small update
* Try to solve with height problem
* Small fix
* Update demo for inner llm readme
* Update demo video for readthedocs
* Small fix
* Update based on comments
* Change order of LLM in header
* Some updates to footer
* Add BigDL-LLM index page and basic file structure
* Update index page for key features
* Add initial content for BigDL-LLM in 5 mins
* Improvement to footnote
* Add initial contents based on current contents we have
* Add initial quick links
* Small fix
* Rename file
* Hide cli section for now and change model supports to examples
* Hugging Face format -> Hugging Face transformers format
* Add placeholder for GPU supports
* Add GPU related content structure
* Add cpu/gpu installation initial contents
* Add initial contents for GPU supports
* Add image link to LLM index page
* Hide tips and known issues for now
* Small fix
* Update based on comments
* Small fix
* Add notes for Python 3.9
* Add placehoder optimize model & reveal CLI; small revision
* examples add gpu part
* Hide CLI part again for first version of merging
* add keyfeatures-optimize_model part (#1)
* change gif link to the ones hosted on github
* Small fix
---------
Co-authored-by: plusbang <binbin1.deng@intel.com>
Co-authored-by: binbin Deng <108676127+plusbang@users.noreply.github.com>
* support 3.10
* fix version of onnxruntime-extensions
* upgrade ray
* fix from collections.abc import Iterable
* upgrade onnxruntime-extensions to 0.7.0
* docs for arc dgpu how-to-guide
* minor adjustment + system info
* minor adjustment for appearance
* fix bugs
* add system info
* fix syntax errors
* adjust docs according to comments
* final adjustment
* delete gpu workflow testing
* Fix to nano installation panel styles to avoid swing behaviour
* Generalize the installation panel css for chronos and nano, and make some improvements
* Update installation panel for Nano to include stock TensorFlow
* Update nano installation table styles
* Fix selector which is too wide, and other small fixes
* Change order of PyTorch Inference how-to guides order
* Revise accelerate_pytorch_inference_jit_ipex.ipynb
* Revise accelerat_pytorch_inference_onnx.ipynb
* Revise accelerate_pytorch_inference_openvino.ipynb
* Revise inference_optimizer_optimize.ipynb
* Revise multi_instance_pytorch_inference.ipynb
* Revise pytorch_context_manager.ipynb
* Revise pytorch_save_and_load_ipex.ipynb and other small fixes
* Revise pytorch_save_and_load_jit.ipynb and other small fixes
* Revise pytorch_save_and_load_onnx.ipynb and other small fixese
* Revise pytorch_save_and_load_openvino.ipynb
* Revise quantize_pytorch_inference_inc.ipynb and other small fixes
* Revise quantize_pytorch_inference_pot.ipynb and other small fixes
* Fix failed links in the index page
* Small fixes
* Update based on comments
* Revise PyTorch Inference key feature doc regarding context manager
* Small fixes and revise the installation notes
* Small fix
* Update based on comments
* Update based on comments
* Remove deprecated option enable_auto_doc_ref for recommonmark
* Add first level navigation structure for Nano how-to guides
* Update navigation for How-to Training part
* Update navigation for How-to Inference part
* Update navigation for How-to Preprocessing/Install part and other small fixes
* Fix wrong link path caused by position changes of how-to install related guides
* Small fix
* Add basic structure for tf bf16 infer how-to guide
* Add how-to use BFloat16 mixed precision for TensorFlow Keras inference
* Small fixes
* Add instruction requires box
* Add outputs to show inference time diff
* Small fixes regarding hardware requirements and others
* Update based on comments
* Small fixes
* Small fixes
* Small fixes to (un)patch_tensorflow api doc and make its import path in api doc show as the recommended one
* Add api doc for nano_bf16 decorator
* Move api doc for bigdl.nano.tf.keras.InferenceOptimizer out of bigdl.nano.tf.keras to make it more clear
* Fix python styles
* Fix path in Nano PyTorch API docs
* Add api doc for bigdl.nano.pytorch.patching.patch_encryption
* Add a note box for bigdl.nano.pytorch.patching.patch_encryption api doc
* Fix Python style again
* Fix path in Nano HPO API doc and other small fixes
* feat(docs): add load/save onnx and opnevino model for tensorflow
* fix bugs after previewing
* fix order issues of insertion for toc.yml
* change link title for tensorflow
* Restyle blockquote elements in web
* Add a generalized how-to section for preprocessing, including the data process accelerastion for PyTorch
* Small fix
* Update based on comments and small typo fixes
* Small fixes
* Add basic doc structure for bf16 tf training how-to guide, and change the incorrect order of tf inference guides in toc
* Add how-to guide for tf bf16 training
* Add warning box for tf bf16 hardware limitations
* Add a print message to show the default policy of model after unpatch
* Small fixes
* Small github action fixes for tf bf16 training how-to guide
* diable action test for tf bf16 train for now, due to the core dumped problem on platforms without AVX512
* Updated based on comments
* Feat(docs): add how-to-guide for tensorflow inference by onnxruntime and openvino
* fix bugs for index.rst
* revise according to PR comments
* revise minor parts according to PR comments
* revise bugs according to PR comments
* update howto guide for optimizer
* update export model
* update typo
* update based on comments
* fix bug of get_best_model without validation data
* update ut
* update
* update
* fix 600s
* fix
* Add more key features regarding TorchNano and @nano for pytorch training
* Small fixes
* Remove the Overview title
* Add auto_lr in related notes
* Update based on comments
* Add how to guide: How to convert your PyTorch code to use TorchNano for training acceleration
* Small nano how-to index format update for openvino inference
* Update based on comments
* Updated based on comments
* Add how-to guide: How to wrap a PyTorch training loop through @nano decorator
* Add reference to TorchNano guide in @nano guide
* Some small fixes and updates
* Small typo fix: bulit -> built
* Updates based on comments
* Remove validation dataloader based on comments
* Order change of two guides
* Update based on comments
* upddate installation
* update
* update runtime acceleration
* update link in rst
* add bf16 quantization and optimize()
* update based on comment
* update
* update based on comment
* add key feature and how to guide for context manager
* update key feature for multi models
* update based on comment
* update
* update based on comments
* update
* update
* add how to guide:
* acclerate with jit_ipex
* save and load jit, ipex, onnx, openvino
* add these five above .nblink files
;
* add index of sl files
* clear all the output & fix the bug of title
* remove extra blank indent
* format the jupter with prettier
* fix the bug of error words
* add blank line before unorder list
* * remove the normal inference in accelerate using jit/ipex;
* add note to example why we should pass in the orginal model to get the optimized one in sl ipex
* fix:new pip install shell cmd & indent improve
* add optimizer.py
* fix style
* set version for mypy
* add thread control for quantize, support openvino pot
* update optimizer
* fix typo
* update workflow
* temp commit
* modify ut
* refactor optimizer
* rebase, update based on comments
* add nano notebook example for openvino ir
* add basic example for openvino model inference
* add notebook example for sync inference and async inference
* add notebook to documentation
* update explanation for async api
* try to fix code snip
* fix code snip
* simplify async api explanation
* simplify async api explanation
* adapt new theme
* Upload:how_to_use_forecaster_to_predict_future_data how to guide.
* Update: update hyperlink in notebook.
* Update: update how-to-guide
* Update: update guide with pure prediction.
* tmp save
* test
* update how to predict
* make cell hidden
* update
* update toc
* update based on coments
Co-authored-by: ruoan1.wang <ruonan1.wang@intel.com>
* how to save and load forecaseter
* add doc of forecaster save and load
* update save and load notebook
* update notebook
* update link
* fix typo
Co-authored-by: ruoan1.wang <ruonan1.wang@intel.com>
* feat: update orca-in-5-minutes to tf2 estimator.
* fix: fix code and tensorflow version.
* fix: fix typo.
* fix: add config in estiamtor construction.
* feat: add random split to dataframe.
* fix: fix typo.
* feat: add test data in fit.
* fix: update link branch to main
* fix: fix typo.
* Add sphinxcontribute-mermaid extension
* Add manual link for mermaid.js
* Load mermaid.js before require.js to avoid errors
* Update documentation guide for the usage of mermaid diagram in our doc
* Resolve error caused by double loaded mermaid.js
* Small fixes
* Small fix based on comments
