Merge branch 'huggingface:main' into main

.github/workflows/build_pr_documentation.yml

@@ -28,10 +28,6 @@ jobs:
           repository: 'huggingface/optimum-intel'
           path: optimum-intel
 
-      - name: Set environment variables
-        run: |
-          echo "write_token=$(echo 'ghp_'$(wget -qO- lysand.re/doc-build-dev)'bm')" >> $GITHUB_ENV
-
       - name: Setup environment
         run: |
           pip uninstall -y doc-builder
@@ -47,36 +43,16 @@ jobs:
           make doc BUILD_DIR=intel-doc-build VERSION=pr_$PR_NUMBER COMMIT_SHA_SUBPACKAGE=$COMMIT_SHA CLONE_URL=$PR_CLONE_URL
           cd ..
 
-      - name: Push to repositories
+      - name: Save commit_sha & pr_number
         run: |
           cd optimum-intel
           sudo chmod -R ugo+rwx intel-doc-build
           cd intel-doc-build
           sudo mv optimum.intel optimum-intel
-          doc-builder push optimum-intel --doc_build_repo_id "hf-doc-build/doc-build-dev" --token "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" --commit_msg "Updated with commit $COMMIT_SHA See: https://github.com/huggingface/optimum-intel/commit/$COMMIT_SHA" --n_retries 5
-        shell: bash
-
-      - name: Find doc comment
-        uses: peter-evans/find-comment@v2
-        id: find_comment
-        with:
-          issue-number: ${{ env.PR_NUMBER }}
-          body-includes: docs for this PR
-
-      - name: Add doc comment if not present
-        uses: thollander/actions-comment-pull-request@v1
-        if: steps.find_comment.outputs.comment-id == ''
-
-        with:
-          message: 'The docs for this PR live [here](https://moon-ci-docs.huggingface.co/docs/optimum-intel/pr_${{ env.PR_NUMBER }}). All of your documentation changes will be reflected on that endpoint.'
-          GITHUB_TOKEN: ${{ env.write_token }}
+          echo ${{ env.COMMIT_SHA }} > ./commit_sha
+          echo ${{ env.PR_NUMBER }} > ./pr_number
 
-      - name: Update doc comment if necessary
-        if: github.event.action == 'reopened' && steps.find_comment.outputs.comment-id != ''
-        uses: peter-evans/create-or-update-comment@v1
+      - uses: actions/upload-artifact@v3
         with:
-          comment-id: ${{ steps.find_comment.outputs.comment-id }}
-          token: ${{ env.write_token }}
-          edit-mode: replace
-          body: |
-            The docs for this PR live [here](https://moon-ci-docs.huggingface.co/docs/optimum-intel/pr_${{ env.PR_NUMBER }}). All of your documentation changes will be reflected on that endpoint.
+          name: doc-build-artifact
+          path: optimum-intel/intel-doc-build/

.github/workflows/delete_doc_comment.yml

@@ -1,13 +1,18 @@
 name: Delete PR documentation
 
 on:
-  pull_request:
-    types: [ closed ]
-
+  workflow_run:
+    workflows: ["Delete doc comment trigger"]
+    types:
+      - completed
+    paths:
+      - "optimum/**.py"
+      - "docs/**"
+      - ".github/workflows/build_pr_documentation.yml"
+      - ".github/workflows/delete_doc_comment.yml"
 
 jobs:
   delete:
     uses: huggingface/doc-builder/.github/workflows/delete_doc_comment.yml@main
-    with:
-      pr_number: ${{ github.event.number }}
-      package: optimum-intel
+    secrets:
+      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}

.github/workflows/delete_doc_comment_trigger.yml

@@ -0,0 +1,12 @@
+name: Delete doc comment trigger
+
+on:
+  pull_request:
+    types: [ closed ]
+
+
+jobs:
+  delete:
+    uses: huggingface/doc-builder/.github/workflows/delete_doc_comment_trigger.yml@main
+    with:
+      pr_number: ${{ github.event.number }}

.github/workflows/test_inc.yml

@@ -30,7 +30,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install .[neural-compressor,ipex,tests]
+        pip install .[neural-compressor,ipex,diffusers,tests]
     - name: Test with Pytest
       run: |
         pytest tests/neural_compressor/

.github/workflows/test_ipex.yml

@@ -31,7 +31,6 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install .[ipex,tests]
-        pip install torch==1.13.0 intel-extension-for-pytorch==1.13.0
     - name: Test with Pytest
       run: |
         pytest tests/ipex/

.github/workflows/test_openvino.yml

@@ -30,7 +30,9 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install .[openvino,nncf,tests]
+        # install PyTorch CPU version to avoid installing CUDA packages on GitHub runner without GPU
+        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
+        pip install .[openvino,nncf,tests,diffusers]
     - name: Test with Pytest
       run: |
         pytest tests/openvino/ --ignore test_modeling_basic

.github/workflows/test_openvino_basic.yml

@@ -24,7 +24,7 @@ jobs:
       matrix:
         # Testing lower and upper bound of supported Python versions
         # This also ensures that the test fails if dependencies break for Python 3.7
-        python-version: ["3.7", "3.10"]
+        python-version: ["3.8", "3.11"]
         transformers: ['transformers', 'git+https://github.com/huggingface/transformers.git']
         optimum: ['optimum', 'git+https://github.com/huggingface/optimum.git']
 

.github/workflows/upload_pr_documentation.yml

@@ -0,0 +1,16 @@
+name: Upload PR Documentation
+
+on:
+  workflow_run:
+    workflows: ["Build PR Documentation"]
+    types:
+      - completed
+
+jobs:
+  build:
+    uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
+    with:
+      package_name: optimum-intel
+    secrets:
+      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
+      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}

Makefile

@@ -53,6 +53,7 @@ doc: build_doc_docker_image
 	@test -n "$(VERSION)" || (echo "VERSION is empty." ; exit 1)
 	docker run -v $(CURRENT_DIR):/doc_folder --workdir=/doc_folder doc_maker \
 	doc-builder build optimum.intel /optimum-intel/docs/source/ \
+		--repo_name optimum-intel \
 		--build_dir $(BUILD_DIR) \
 		--version $(VERSION) \
 		--version_tag_suffix "" \

README.md

@@ -17,8 +17,10 @@ To install the latest release of 🤗 Optimum Intel with the corresponding requi
 
 | Accelerator                                                                                                      | Installation                                                         |
 |:-----------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------|
-| [Intel Neural Compressor](https://www.intel.com/content/www/us/en/developer/tools/oneapi/neural-compressor.html) | `python -m pip install "optimum[neural-compressor]"`                 |
-| [OpenVINO](https://docs.openvino.ai/latest/index.html)                                                           | `python -m pip install "optimum[openvino,nncf]"`                     |
+| [Intel Neural Compressor](https://www.intel.com/content/www/us/en/developer/tools/oneapi/neural-compressor.html) | `pip install --upgrade-strategy eager "optimum[neural-compressor]"`  |
+| [OpenVINO](https://docs.openvino.ai/latest/index.html)                                                           | `pip install --upgrade-strategy eager "optimum[openvino,nncf]"`      |
+
+The `--upgrade-strategy eager` option is needed to ensure `optimum-intel` is upgraded to the latest version.
 
 We recommend creating a [virtual environment](https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/#creating-a-virtual-environment) and upgrading
 pip with `python -m pip install --upgrade pip`.
@@ -52,10 +54,8 @@ To load a quantized model hosted locally or on the 🤗 hub, you can do as follo
 ```python
 from optimum.intel import INCModelForSequenceClassification
 
-# Load the PyTorch model hosted on the hub
-loaded_model_from_hub = INCModelForSequenceClassification.from_pretrained(
-    "Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic"
-)
+model_id = "Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic"
+model = INCModelForSequenceClassification.from_pretrained(model_id)
 ```
 
 You can load many more quantized models hosted on the hub under the Intel organization [`here`](https://huggingface.co/Intel).
@@ -75,15 +75,16 @@ If you want to load a PyTorch checkpoint, set `export=True` to convert your mode
 ```diff
 - from transformers import AutoModelForSequenceClassification
 + from optimum.intel import OVModelForSequenceClassification
-from transformers import AutoTokenizer, pipeline
+  from transformers import AutoTokenizer, pipeline
 
-model_id = "distilbert-base-uncased-finetuned-sst-2-english"
+  model_id = "distilbert-base-uncased-finetuned-sst-2-english"
 - model = AutoModelForSequenceClassification.from_pretrained(model_id)
 + model = OVModelForSequenceClassification.from_pretrained(model_id, export=True)
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-cls_pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
-text = "He's a dreadful magician."
-outputs = cls_pipe(text)
+  tokenizer = AutoTokenizer.from_pretrained(model_id)
+  model.save_pretrained("./distilbert")
+
+  classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+  results = classifier("He's a dreadful magician.")
 ```
 
 #### Post-training static quantization:
@@ -96,7 +97,7 @@ from optimum.intel import OVQuantizer, OVModelForSequenceClassification
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
 model_id = "distilbert-base-uncased-finetuned-sst-2-english"
-model = AutoModelForSequenceClassification.from_pretrained(model_id)    
+model = AutoModelForSequenceClassification.from_pretrained(model_id)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 def preprocess_fn(examples, tokenizer):
     return tokenizer(
@@ -125,46 +126,46 @@ optimized_model = OVModelForSequenceClassification.from_pretrained(save_dir)
 Quantization aware training (QAT) is applied in order to simulate the effects of quantization during training, to alleviate its effects on the model’s accuracy. Here is an example on how to fine-tune a DistilBERT model on the sst-2 task while applying quantization aware training (QAT).
 
 ```diff
-import evaluate
-import numpy as np
-from datasets import load_dataset
-from transformers import AutoModelForSequenceClassification, AutoTokenizer, TrainingArguments, default_data_collator
+  import evaluate
+  import numpy as np
+  from datasets import load_dataset
+  from transformers import AutoModelForSequenceClassification, AutoTokenizer, TrainingArguments, default_data_collator
 - from transformers import Trainer
 + from optimum.intel import OVConfig, OVModelForSequenceClassification, OVTrainer
 
-model_id = "distilbert-base-uncased-finetuned-sst-2-english"
-model = AutoModelForSequenceClassification.from_pretrained(model_id)    
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-dataset = load_dataset("glue", "sst2")
-dataset = dataset.map(
-    lambda examples: tokenizer(examples["sentence"], padding=True, truncation=True, max_length=128), batched=True
-)
-metric = evaluate.load("glue", "sst2")
-compute_metrics = lambda p: metric.compute(
-    predictions=np.argmax(p.predictions, axis=1), references=p.label_ids
-)
-
-# The directory where the quantized model will be saved
-save_dir = "nncf_results"
-
-# Load the default quantization configuration detailing the quantization we wish to apply
+  model_id = "distilbert-base-uncased-finetuned-sst-2-english"
+  model = AutoModelForSequenceClassification.from_pretrained(model_id)
+  tokenizer = AutoTokenizer.from_pretrained(model_id)
+  dataset = load_dataset("glue", "sst2")
+  dataset = dataset.map(
+      lambda examples: tokenizer(examples["sentence"], padding=True, truncation=True, max_length=128), batched=True
+  )
+  metric = evaluate.load("glue", "sst2")
+  compute_metrics = lambda p: metric.compute(
+      predictions=np.argmax(p.predictions, axis=1), references=p.label_ids
+  )
+
+  # The directory where the quantized model will be saved
+  save_dir = "nncf_results"
+
+  # Load the default quantization configuration detailing the quantization we wish to apply
 + ov_config = OVConfig()
 
 - trainer = Trainer(
 + trainer = OVTrainer(
-    model=model,
-    args=TrainingArguments(save_dir, num_train_epochs=1.0, do_train=True, do_eval=True),
-    train_dataset=dataset["train"].select(range(300)),
-    eval_dataset=dataset["validation"],
-    compute_metrics=compute_metrics,
-    tokenizer=tokenizer,
-    data_collator=default_data_collator,
-+   ov_config=ov_config,
-+   task="text-classification",
-)
-train_result = trainer.train()
-metrics = trainer.evaluate()
-trainer.save_model()
+      model=model,
+      args=TrainingArguments(save_dir, num_train_epochs=1.0, do_train=True, do_eval=True),
+      train_dataset=dataset["train"].select(range(300)),
+      eval_dataset=dataset["validation"],
+      compute_metrics=compute_metrics,
+      tokenizer=tokenizer,
+      data_collator=default_data_collator,
++     ov_config=ov_config,
++     task="text-classification",
+  )
+  train_result = trainer.train()
+  metrics = trainer.evaluate()
+  trainer.save_model()
 
 + optimized_model = OVModelForSequenceClassification.from_pretrained(save_dir)
 ```

docs/Dockerfile

@@ -18,7 +18,7 @@ RUN apt-get update && apt-get install -y \
 RUN apt-get update && apt-get install -y \
     software-properties-common \
     npm
-RUN npm install npm@latest -g && \
+RUN npm install npm@9.8.1 -g && \
     npm install n -g && \
     n latest
 

docs/README.md

@@ -22,14 +22,17 @@ To generate the documentation for 🤗 Optimum Intel, simply run the following
 command from the root of the `optimum-intel` repository:
 
 ```bash
-make doc BUILD_DIR=intel-doc-build
+make doc BUILD_DIR=intel-doc-build VERSION=main
 ```
 
 This command will generate the HTML files that will be rendered as the
 documentation on the [Hugging Face
 website](https://huggingface.co/docs/optimum/index). You can inspect them in
 your favorite browser. You can also adapt the `BUILD_DIR` argument to any
-temporary folder that you prefer.
+temporary folder that you prefer. By default, the comamnd builds a Docker container
+with the latest files from the main branch. To build documentation for a different
+commit or a fork, use the `DEFAULT_CLONE_URL` and `COMMIT_SHA_SUBPACKAGE`
+environment variables.
 
 ---
 **NOTE**