Update to 2.3.0 (#1539)

.github/workflows/script/unitTest/run_unit_test_neuralchat.sh

@@ -89,7 +89,7 @@ function main() {
     apt-get install libsm6 libxext6 -y
     wget http://nz2.archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.19_amd64.deb
     dpkg -i libssl1.1_1.1.1f-1ubuntu2.19_amd64.deb
-    python -m pip install --upgrade --force-reinstall torch==2.2.0
+    python -m pip install --upgrade --force-reinstall torch==2.3.0
     python -m pip install fastapi==0.103.2
     cd ${WORKING_DIR} || exit 1
     echo "test on ${test_name}"

docker/Dockerfile_chatbot

@@ -56,7 +56,7 @@ COPY ${REPO_PATH} /intel-extension-for-transformers
 RUN if [ "$REPO_PATH" == "" ]; then rm -rf intel-extension-for-transformers/* && rm -rf intel-extension-for-transformers/.* ; git clone --single-branch --branch=${ITREX_VER} ${REPO} intel-extension-for-transformers ; fi
 WORKDIR /intel-extension-for-transformers
 
-RUN pip install oneccl_bind_pt --extra-index-url  https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
+RUN pip install oneccl_bind_pt==2.3.0 --extra-index-url  https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
     cd /intel-extension-for-transformers && pip install -r requirements.txt && \
     python setup.py install && \
     cd ./intel_extension_for_transformers/neural_chat/examples/finetuning/instruction && pip install -r requirements.txt && \

docker/Dockerfile_code_gen

@@ -49,7 +49,7 @@ COPY . /app/intel-extension-for-transformers
 
 RUN ${PYTHON} -m pip install -r requirements.txt --no-cache-dir -f https://download.pytorch.org/whl/cpu/torch_stable.html
 
-RUN ${PYTHON} -m pip install torch==2.2.0+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html
+RUN ${PYTHON} -m pip install torch==2.3.0+cpu -f https://download.pytorch.org/whl/cpu/torch_stable.html
 
 RUN ${PYTHON} -m pip install -r examples/huggingface/pytorch/code-generation/quantization/requirements.txt --no-cache-dir
 

examples/huggingface/neural_speed/perplexity/requirements.txt

@@ -1,5 +1,5 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.2.0+cpu
+torch==2.3.0+cpu
 transformers
 numpy
 sentencepiece

examples/huggingface/neural_speed/requirements.txt

@@ -4,8 +4,8 @@ lm-eval
 sentencepiece
 gguf
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.2.0+cpu
+torch==2.3.0+cpu
 transformers
-intel_extension_for_pytorch==2.2.0
+intel_extension_for_pytorch==2.3.0
 tiktoken
 transformers_stream_generator

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

@@ -4,12 +4,12 @@ datasets >= 2.0
 protobuf
 sentencepiece != 0.1.92
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.2.0+cpu
+torch==2.3.0+cpu
 peft==0.6.2
 transformers >= 4.35.0
 tiktoken #code_gen
 neural-compressor
-intel_extension_for_pytorch==2.2.0
+intel_extension_for_pytorch==2.3.0
 optimum-intel
 auto-round
 git+https://github.com/bigcode-project/bigcode-evaluation-harness@094c7cc197d13a53c19303865e2056f1c7488ac1

examples/huggingface/pytorch/image-classification/deployment/imagenet/vit/requirements.txt

@@ -4,8 +4,8 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
-torchvision==0.17.0
+torch==2.3.0
+torchvision==0.18.0
 onnx>=1.12
 onnxruntime==1.13.1
 onnxoptimizer

examples/huggingface/pytorch/image-classification/quantization/requirements.txt

@@ -3,8 +3,8 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
-torchvision==0.17.0
+torch==2.3.0
+torchvision==0.18.0
 onnx>=1.12
 onnxruntime==1.13.1
 evaluate

examples/huggingface/pytorch/language-modeling/deployment/fill-mask/electra_base_chinese/requirements.txt

@@ -1,4 +1,4 @@
 transformers
-torch==2.2.0
+torch==2.3.0
 optimum
 accelerate

examples/huggingface/pytorch/question-answering/deployment/squad/bert_large/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/question-answering/deployment/squad/length_adaptive_transformer/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.12.1
 optimum

examples/huggingface/pytorch/question-answering/dynamic/requirements.txt

@@ -1,6 +1,6 @@
 transformers
 datasets
 torchprofile
-torch==2.2.0
-intel_extension_for_pytorch==2.2.0
+torch==2.3.0
+intel_extension_for_pytorch==2.3.0
 accelerate

examples/huggingface/pytorch/question-answering/pruning/basic_magnitude/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.8.0
-torch==2.2.0
+torch==2.3.0
 transformers
 wandb
 accelerate

examples/huggingface/pytorch/question-answering/pruning/longformer_triviaqa/requirements.txt

@@ -1,5 +1,5 @@
 accelerate
 datasets
 transformers
-torch==2.2.0
+torch==2.3.0
 neural-compressor==2.0

examples/huggingface/pytorch/summarization/quantization/requirements.txt

@@ -4,7 +4,7 @@ sentencepiece != 0.1.92
 rouge-score
 nltk
 py7zr
-torch==2.2.0
+torch==2.3.0
 transformers
 protobuf
 schema

examples/huggingface/pytorch/text-classification/cascade-models/requirements.txt

@@ -1,4 +1,4 @@
-torch==2.2.0
+torch==2.3.0
 numpy
 transformers
 datasets

examples/huggingface/pytorch/text-classification/deployment/emotion/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base_cased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_mini/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/mrpc/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/mrpc/roberta_base/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/sparse/bert_mini/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/sparse/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/sst2/bert_mini/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/sst2/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/deployment/sst2/minilm_l6_h384_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 optimum

examples/huggingface/pytorch/text-classification/early-exit/requirements.txt

@@ -1,4 +1,4 @@
-torch==2.2.0
+torch==2.3.0
 transformers
 datasets
 allennlp

examples/huggingface/pytorch/text-classification/new_pruning/requirements.txt

@@ -6,5 +6,5 @@ sentencepiece
 scipy
 scikit-learn
 protobuf
-torch==2.2.0
+torch==2.3.0
 evaluate

examples/huggingface/pytorch/text-classification/orchestrate_optimizations/requirements.txt

@@ -1,5 +1,5 @@
 accelerate
-torch==2.2.0
+torch==2.3.0
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 transformers

examples/huggingface/pytorch/text-classification/pruning/requirements.txt

@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 transformers
 wandb

examples/huggingface/pytorch/text-classification/quantization/ptq/requirements.txt

@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 transformers
 wandb

examples/huggingface/pytorch/text-classification/quantization/qat/requirements.txt

@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 transformers
 wandb

examples/huggingface/pytorch/text-classification/quantization/requirements.txt

@@ -2,6 +2,6 @@ accelerate
 datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 transformers
 wandb

examples/huggingface/pytorch/text-embedding/deployment/mteb/bge/requirements.txt

@@ -3,7 +3,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx
 onnxruntime==1.13.1
 mteb==1.1.1

examples/huggingface/pytorch/text-generation/quantization/llm_quantization_recipes.md

@@ -42,8 +42,8 @@ cd examples/huggingface/pytorch/text-generation/quantization
 pip install -r requirements.txt
 pip install neural-compressor==2.5
 pip install transformers==4.35.2
-pip install torch==2.2.0+cpu --index-url https://download.pytorch.org/whl/cpu
-pip install intel-extension-for-pytorch==2.2.0
+pip install torch==2.3.0+cpu --index-url https://download.pytorch.org/whl/cpu
+pip install intel-extension-for-pytorch==2.3.0
 ```
 
 # Run Quantization and evaluate INT8 accuracy

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

@@ -4,7 +4,7 @@ peft
 protobuf
 sentencepiece != 0.1.92
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.2.0+cpu
+torch==2.3.0+cpu
 transformers
 bitsandbytes  #baichuan
 transformers_stream_generator

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

@@ -4,9 +4,9 @@ peft
 protobuf
 sentencepiece != 0.1.92
 --extra-index-url https://download.pytorch.org/whl/cpu
-torch==2.2.0+cpu
+torch==2.3.0+cpu
 transformers
-intel_extension_for_pytorch==2.2.0
+intel_extension_for_pytorch==2.3.0
 git+https://github.com/huggingface/optimum.git@e38d40ad220a180213f99b1d93d0407a826c326d
 optimum-intel
 bitsandbytes  #baichuan

examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==2.2.0
+torch==2.3.0
 onnx>=1.12
 onnxruntime==1.13.1
 diffusers==0.12.1

examples/huggingface/pytorch/textual-inversion/quantization/requirements.txt

@@ -1,9 +1,9 @@
 diffusers==0.4.1
 accelerate
-torch==2.2.0
-torchvision==0.17.0
+torch==2.3.0
+torchvision==0.18.0
 transformers
 ftfy
 tensorboard
 modelcards
-intel_extension_for_pytorch==2.2.0
+intel_extension_for_pytorch==2.3.0

examples/huggingface/pytorch/token-classification/quantization/requirements.txt

@@ -1,6 +1,6 @@
 accelerate
 seqeval
 datasets >= 1.1.3
-torch==2.2.0
+torch==2.3.0
 transformers
 wandb

examples/huggingface/pytorch/translation/quantization/requirements.txt

@@ -4,5 +4,5 @@ sentencepiece != 0.1.92
 protobuf
 sacrebleu >= 1.4.12
 py7zr
-torch==2.2.0
+torch==2.3.0
 transformers

intel_extension_for_transformers/llm/runtime/neural_speed/requirements.txt

@@ -12,6 +12,6 @@ protobuf<3.20
 py-cpuinfo
 sentencepiece
 tiktoken
-torch==2.2.0+cpu
+torch==2.3.0+cpu
 transformers
 transformers_stream_generator

intel_extension_for_transformers/neural_chat/docker/Dockerfile

@@ -56,7 +56,7 @@ COPY ${REPO_PATH} /intel-extension-for-transformers
 RUN if [ "$REPO_PATH" == "" ]; then rm -rf intel-extension-for-transformers/* && rm -rf intel-extension-for-transformers/.* ; git clone --single-branch --branch=${ITREX_VER} ${REPO} intel-extension-for-transformers ; fi
 WORKDIR /intel-extension-for-transformers
 
-RUN pip install oneccl_bind_pt --extra-index-url  https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
+RUN pip install oneccl_bind_pt==2.3.0 --extra-index-url  https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
     cd /intel-extension-for-transformers && pip install schema==0.7.5 numpy==1.26.4 && \
     python setup.py install && \
     cd ./intel_extension_for_transformers/neural_chat/examples/finetuning/instruction && pip install -r requirements.txt && \

intel_extension_for_transformers/neural_chat/docker/code_generation/cpu/Dockerfile

@@ -45,7 +45,7 @@ COPY ${REPO_PATH} /intel-extension-for-transformers
 RUN if [ "$REPO_PATH" == "" ]; then rm -rf intel-extension-for-transformers/* && rm -rf intel-extension-for-transformers/.* ; git clone --single-branch --branch=${ITREX_VER} ${REPO} intel-extension-for-transformers ; fi
 WORKDIR /intel-extension-for-transformers
 
-RUN pip install oneccl_bind_pt --extra-index-url  https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
+RUN pip install oneccl_bind_pt==2.3.0 --extra-index-url  https://pytorch-extension.intel.com/release-whl/stable/cpu/us/ && \
     cd /intel-extension-for-transformers && pip install -r requirements.txt && python setup.py install && \
     cd ./intel_extension_for_transformers/neural_chat/examples/finetuning/instruction && pip install -r requirements.txt && \
     cd /intel-extension-for-transformers/intel_extension_for_transformers/neural_chat && pip install -r requirements_cpu.txt && \