Merge branch 'main' into modelscope_for_itrex

.github/checkgroup.yml

@@ -65,54 +65,54 @@ subprojects:
       - "engine-unit-test-PR-test"
       - "Genreate-Engine-Report"
 
-  - id: "Windows Binary Test"
-    paths:
-      - ".github/workflows/windows-test.yml"
-      - "requirements.txt"
-      - "setup.py"
-      - "intel_extension_for_transformers/transformers/runtime/**"
-      - "intel_extension_for_transformers/transformers/llm/operator/**"
-      - "!intel_extension_for_transformers/transformers/runtime/third_party/**"
-      - "!intel_extension_for_transformers/transformers/runtime/docs/**"
-      - "!intel_extension_for_transformers/transformers/runtime/test/**"
-    checks:
-      - "Windows-Binary-Test"
+  # - id: "Windows Binary Test"
+  #   paths:
+  #     - ".github/workflows/windows-test.yml"
+  #     - "requirements.txt"
+  #     - "setup.py"
+  #     - "intel_extension_for_transformers/transformers/runtime/**"
+  #     - "intel_extension_for_transformers/transformers/llm/operator/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/third_party/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/docs/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/test/**"
+  #   checks:
+  #     - "Windows-Binary-Test"
 
-  - id: "LLM Model Test workflow"
-    paths:
-      - ".github/workflows/llm-test.yml"
-      - ".github/workflows/script/models/run_llm.sh"
-      - "intel_extension_for_transformers/transformers/runtime/**"
-      - "!intel_extension_for_transformers/transformers/runtime/kernels/**"
-      - "!intel_extension_for_transformers/transformers/runtime/test/**"
-      - "!intel_extension_for_transformers/transformers/runtime/third_party/**"
-      - "!intel_extension_for_transformers/transformers/runtime/docs/**"
-    checks:
-      - "LLM-Workflow (gpt-j-6b, engine, latency, bf16,int8,fp8)"
-      - "Generate-LLM-Report"
+  # - id: "LLM Model Test workflow"
+  #   paths:
+  #     - ".github/workflows/llm-test.yml"
+  #     - ".github/workflows/script/models/run_llm.sh"
+  #     - "intel_extension_for_transformers/transformers/runtime/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/kernels/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/test/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/third_party/**"
+  #     - "!intel_extension_for_transformers/transformers/runtime/docs/**"
+  #   checks:
+  #     - "LLM-Workflow (gpt-j-6b, engine, latency, bf16,int8,fp8)"
+  #     - "Generate-LLM-Report"
 
-  - id: "Chat Bot Test workflow"
-    paths:
-      - ".github/workflows/chatbot-test.yml"
-      - ".github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml"
-      - ".github/workflows/chatbot-inference-mpt-7b-chat.yml"
-      - ".github/workflows/chatbot-finetune-mpt-7b-chat.yml"
-      - ".github/workflows/chatbot-inference-llama-2-7b-chat-hf-hpu.yml"
-      - ".github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml"
-      - ".github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml"
-      - ".github/workflows/script/chatbot/**"
-      - ".github/workflows/sample_data/**"
-      - "intel_extension_for_transformers/neural_chat/**"
-      - "intel_extension_for_transformers/transformers/llm/finetuning/**"
-      - "intel_extension_for_transformers/transformers/llm/quantization/**"
-      - "intel_extension_for_transformers/transformers/**"
-      - "workflows/chatbot/inference/**"
-      - "workflows/chatbot/fine_tuning/**"
-      - "!intel_extension_for_transformers/neural_chat/docs/**"
-      - "!intel_extension_for_transformers/neural_chat/tests/ci/**"
-      - "!intel_extension_for_transformers/neural_chat/examples/**"
-      - "!intel_extension_for_transformers/neural_chat/assets/**"
-      - "!intel_extension_for_transformers/neural_chat/README.md"
-    checks:
-      - "call-inference-llama-2-7b-chat-hf / inference test"
-      - "call-inference-mpt-7b-chat / inference test"
+  # - id: "Chat Bot Test workflow"
+  #   paths:
+  #     - ".github/workflows/chatbot-test.yml"
+  #     - ".github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml"
+  #     - ".github/workflows/chatbot-inference-mpt-7b-chat.yml"
+  #     - ".github/workflows/chatbot-finetune-mpt-7b-chat.yml"
+  #     - ".github/workflows/chatbot-inference-llama-2-7b-chat-hf-hpu.yml"
+  #     - ".github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml"
+  #     - ".github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml"
+  #     - ".github/workflows/script/chatbot/**"
+  #     - ".github/workflows/sample_data/**"
+  #     - "intel_extension_for_transformers/neural_chat/**"
+  #     - "intel_extension_for_transformers/transformers/llm/finetuning/**"
+  #     - "intel_extension_for_transformers/transformers/llm/quantization/**"
+  #     - "intel_extension_for_transformers/transformers/**"
+  #     - "workflows/chatbot/inference/**"
+  #     - "workflows/chatbot/fine_tuning/**"
+  #     - "!intel_extension_for_transformers/neural_chat/docs/**"
+  #     - "!intel_extension_for_transformers/neural_chat/tests/ci/**"
+  #     - "!intel_extension_for_transformers/neural_chat/examples/**"
+  #     - "!intel_extension_for_transformers/neural_chat/assets/**"
+  #     - "!intel_extension_for_transformers/neural_chat/README.md"
+  #   checks:
+  #     - "call-inference-llama-2-7b-chat-hf / inference test"
+  #     - "call-inference-mpt-7b-chat / inference test"

.github/workflows/script/formatScan/nlp_dict.txt

@@ -1,5 +1,6 @@
 alse
 ans
+assertIn
 bu
 charactor
 daa

.github/workflows/script/install_binary.sh

@@ -1,4 +1,5 @@
 #!/bin/bash
+
 source /intel-extension-for-transformers/.github/workflows/script/change_color.sh
 
 cd /intel-extension-for-transformers
@@ -10,7 +11,7 @@ git config --global --add safe.directory "*"
 git submodule update --init --recursive
 
 
-$BOLD_YELLOW && echo "---------------- run python setup.py sdist bdist_wheel -------------" && $RESET
+$BOLD_YELLOW && echo "---------------- run python setup.py bdist_wheel -------------" && $RESET
 python setup.py bdist_wheel
 
 

.github/workflows/unit-test-optimize.yml

@@ -67,7 +67,7 @@ jobs:
         with:
           submodules: "recursive"
           ref: ${{ matrix.test_branch }}
-          fetch-tags: true
+          fetch-depth: 0
 
       - name: Docker Build
         run: |

.pre-commit-config.yaml

@@ -4,7 +4,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
       - id: debug-statements
       - id: mixed-line-ending
@@ -44,7 +44,7 @@ repos:
           )$
 
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.3.0
     hooks:
       - id: codespell
         args: [-w, --ignore-words=.github/workflows/script/formatScan/nlp_dict.txt]

docs/code_of_conduct.md

@@ -14,7 +14,7 @@ In the interest of fostering an open and welcoming environment, we as
 contributors and maintainers pledge to making participation in our project and
 our community a harassment-free experience for everyone, regardless of age, body
 size, disability, ethnicity, sex characteristics, gender identity and expression,
-level of experience, education, socio-economic status, nationality, personal
+level of experience, education, socioeconomic status, nationality, personal
 appearance, race, religion, or sexual identity and orientation.
 
 ## Our Standards

examples/huggingface/pytorch/code-generation/quantization/Dockerfile-multiple

@@ -61,7 +61,7 @@ ENV COMPOSE_DOCKER_CLI_BUILD=0
 # Install torch and intel-extension-for-pytorch 2.1
 RUN python3 -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
 RUN python3 -m pip install intel-extension-for-pytorch intel-extension-for-transformers optimum
-RUN python3 -m pip install git+https://github.com/huggingface/optimum-intel.git@f95dea1ae8966dee4d75d622e7b2468c514ba02d
+RUN python3 -m pip install git+https://github.com/huggingface/optimum-intel.git@50d867c13b22c22eda451ddb67bddb8159670f85
 RUN python3 -m pip install git+https://github.com/bigcode-project/bigcode-evaluation-harness@0d84db85f9ff971fa23a187a3347b7f59af288dc
 
 # Standard requirements

examples/huggingface/pytorch/code-generation/quantization/requirements.txt

@@ -10,6 +10,6 @@ transformers >= 4.35.0
 tiktoken #code_gen
 neural-compressor
 intel_extension_for_pytorch==2.3.0
-optimum-intel
+git+https://github.com/huggingface/optimum-intel.git@50d867c13b22c22eda451ddb67bddb8159670f85
 auto-round==0.2
 git+https://github.com/bigcode-project/bigcode-evaluation-harness@094c7cc197d13a53c19303865e2056f1c7488ac1

examples/huggingface/pytorch/question-answering/deployment/squad/MLperf_example/csrc/bert_qsl.cpp

@@ -74,7 +74,7 @@ namespace qsl {
       }
     }
 
-    // Splice them togather
+    // Splice them together
     Queue_t result;
     for (auto& q : Buckets)
       result.splice(result.end(), std::move(q));

examples/huggingface/pytorch/question-answering/deployment/squad/MLperf_example/utils_qa.py

@@ -295,7 +295,7 @@ def postprocess_qa_predictions_with_beam_search(
 
     assert len(predictions[0]) == len(
         features
-    ), f"Got {len(predictions[0])} predicitions and {len(features)} features."
+    ), f"Got {len(predictions[0])} predictions and {len(features)} features."
 
     # Build a map example to its corresponding features.
     example_id_to_index = {k: i for i, k in enumerate(examples["id"])}

examples/huggingface/pytorch/text-generation/quantization/requirements_GPU.txt

@@ -7,7 +7,7 @@ sentencepiece != 0.1.92
 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 torch==2.1.0a0
 transformers
-optimum-intel
+git+https://github.com/huggingface/optimum-intel.git@50d867c13b22c22eda451ddb67bddb8159670f85
 bitsandbytes  #baichuan
 transformers_stream_generator
 tiktoken  #qwen

examples/huggingface/pytorch/text-generation/quantization/requirements_sq.txt

@@ -7,7 +7,7 @@ sentencepiece != 0.1.92
 torch==2.3.0+cpu
 transformers==4.38.1
 intel_extension_for_pytorch==2.3.0
-optimum-intel==1.16.1
+git+https://github.com/huggingface/optimum-intel.git@50d867c13b22c22eda451ddb67bddb8159670f85
 bitsandbytes  #baichuan
 transformers_stream_generator
 tiktoken  #qwen

examples/huggingface/pytorch/text-generation/quantization/run_generation_gpu_woq.py

@@ -142,12 +142,7 @@
 
 user_model = None
 
-# tokenizer
-if config.model_type == "llama":
-   from transformers import LlamaTokenizer
-   tokenizer = LlamaTokenizer.from_pretrained(args.model)
-else:
-   tokenizer = AutoTokenizer.from_pretrained(args.model, trust_remote_code=args.trust_remote_code)
+tokenizer = AutoTokenizer.from_pretrained(args.model, trust_remote_code=args.trust_remote_code)
 
 quantization_config = None
 if args.woq:

examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/ITREX_StableDiffusionInstructPix2PixPipeline.py

@@ -14,7 +14,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Pipeline Modificaiton based from the diffusers 0.12.1 StableDiffusionInstructPix2PixPipeline"""
+"""Pipeline Modification based from the diffusers 0.12.1 StableDiffusionInstructPix2PixPipeline"""
 
 import inspect
 from typing import Callable, List, Optional, Union

examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/README.md

@@ -137,7 +137,7 @@ python run_executor.py --ir_path=./qat_int8_ir --mode=latency --input_model=runw
 ## 3. Accuracy
 Frechet Inception Distance(FID) metric is used to evaluate the accuracy. This case we check the FID scores between the pytorch image and engine image.
 
-By setting --accuracy to check FID socre.
+By setting --accuracy to check FID score.
 Python API command as follows:
 ```python
 # FP32 IR

examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/diffusion_utils_img2img.py

@@ -14,7 +14,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Pipeline Modificaiton based from the diffusers 0.12.1 StableDiffusionImg2ImgPipeline"""
+"""Pipeline Modification based from the diffusers 0.12.1 StableDiffusionImg2ImgPipeline"""
 
 import inspect
 from typing import Callable, List, Optional, Union

intel_extension_for_transformers/neural_chat/docs/notebooks/build_chatbot_on_xpu.ipynb

@@ -77,7 +77,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Install requirements that have denpendency on stock pytorch"
+    "Install requirements that have dependency on stock pytorch"
    ]
   },
   {

intel_extension_for_transformers/neural_chat/docs/notebooks/deploy_chatbot_on_xpu.ipynb

@@ -69,7 +69,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Install requirements that have denpendency on stock pytorch"
+    "Install requirements that have dependency on stock pytorch"
    ]
   },
   {

intel_extension_for_transformers/neural_chat/examples/deployment/photo_ai/backend/README.md

@@ -75,7 +75,7 @@ mkdir /home/nfs_images
 export IMAGE_SERVER_IP="your.server.ip"
 ```
 
-# Configurate photoai.yaml
+# Configure photoai.yaml
 
 You can customize the configuration file `photoai.yaml` to match your environment setup. Here's a table to help you understand the configurable options:
 
@@ -91,9 +91,9 @@ You can customize the configuration file `photoai.yaml` to match your environmen
 | tasks_list          | ['voicechat', 'photoai']               |
 
 
-# Configurate Environment Variables
+# Configure Environment Variables
 
-Configurate all of the environment variables in file `run.sh` using `export XXX=xxx`. Here's a table of all the variables needed to configurate.
+Configure all of the environment variables in file `run.sh` using `export XXX=xxx`. Here's a table of all the variables needed to configure.
 
 |  Variable           | Value                                  |
 | ------------------- | ---------------------------------------|

intel_extension_for_transformers/neural_chat/examples/finetuning/multi_modal/eval/mmmu_eval/main_eval_only.py

@@ -11,7 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Parse and Evalate."""
+"""Parse and Evaluate."""
 import os
 import json
 

intel_extension_for_transformers/neural_chat/examples/finetuning/multi_modal/eval/mmmu_eval/main_parse_and_eval.py

@@ -11,7 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Parse and Evalate."""
+"""Parse and Evaluate."""
 import os
 import json
 import shlex

intel_extension_for_transformers/neural_chat/pipeline/plugins/image2image/instructpix2pix_pipeline.py

@@ -14,7 +14,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Pipeline Modificaiton based from the diffusers 0.12.1 StableDiffusionInstructPix2PixPipeline."""
+"""Pipeline Modification based from the diffusers 0.12.1 StableDiffusionInstructPix2PixPipeline."""
 
 import inspect
 from typing import Callable, List, Optional, Union