Merge branch 'main' into penghuic/woq_loading_issue

.github/checkgroup.yml

@@ -30,13 +30,6 @@ subprojects:
       - "optimize-unit-test-PR-test"
       - "Genreate-OptimizeUT-Report"
 
-  - id: "Neural Speed Unit Test workflow"
-    paths:
-      - .github/workflows/unit-test-neuralspeed.yml
-      - ".github/workflows/script/unitTest/run_unit_test_neuraspeed.sh"
-    checks:
-      - "neural-speed-unit-test"
-
   - id: "NeuralChat Unit Test"
     paths:
       - ".github/workflows/unit-test-neuralchat.yml"

.github/workflows/Scaner_BDBA.yaml

@@ -3,7 +3,6 @@ name: Scanner BDBA
 on:
   workflow_dispatch:
 
-permissions: write-all
 jobs:
   bdba_job:
     name: BDBA Scan

.github/workflows/Scaner_Coverity.yaml

@@ -3,7 +3,6 @@ name: Scanner Coverity PYTHON
 on:
     workflow_dispatch:
 
-permissions: write-all
 jobs:
   coverity_job:
     name: Coverity

.github/workflows/Scaner_Trivy.yaml

@@ -2,7 +2,6 @@ name: Trivy Scan for Containers
 
 on:
     workflow_dispatch:
-permissions: write-all
 jobs:
   trivy_container_job:
     uses: "intel-innersource/frameworks.ai.infrastructure.code-scan-tools/.github/workflows/Scanner_Trivy.yml@one-ci-cd"

.github/workflows/build-container.yaml

@@ -3,7 +3,6 @@ on:
   workflow_dispatch: # Can be manually executed
   schedule: # 1/week Sunday at 07:00AM
     - cron: "5 7 * * 0"
-permissions: write-all
 jobs:
   build:
     container: # MLOps Dev container for Compose Automation

.github/workflows/chatbot-finetune-mpt-7b-chat-hpu.yml

@@ -6,7 +6,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-ft-mpt-7b-hpu
   cancel-in-progress: true
-permissions: write-all
 jobs:
   finetuning:
     name: finetuning test

.github/workflows/chatbot-finetune-mpt-7b-chat.yml

@@ -6,7 +6,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-ft-mpt-7b
   cancel-in-progress: true
-permissions: write-all
 jobs:
   finetuning:
     name: finetuning test

.github/workflows/chatbot-inference-llama-2-7b-chat-hf.yml

@@ -6,7 +6,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-inf-lla-7b
   cancel-in-progress: true
-permissions: write-all
 jobs:
   inference:
     name: inference test

.github/workflows/chatbot-inference-llama-2-7b_70b-chat-hf-hpu.yml

@@ -6,7 +6,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-inf-lla-7b-hpu
   cancel-in-progress: true
-permissions: write-all
 jobs:
   inference:
     name: inference test

.github/workflows/chatbot-inference-mpt-7b-chat-hpu.yml

@@ -6,7 +6,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-inf-mpt-7b-hpu
   cancel-in-progress: true
-permissions: write-all
 jobs:
   inference:
     name: inference test

.github/workflows/chatbot-inference-mpt-7b-chat.yml

@@ -6,7 +6,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-inf-mpt-7b
   cancel-in-progress: true
-permissions: write-all
 jobs:
   inference:
     name: inference test

.github/workflows/chatbot-test.yml

@@ -27,7 +27,6 @@ on:
       - '!intel_extension_for_transformers/neural_chat/README.md'
 
   workflow_dispatch:
-permissions: write-all
 # If there is a new commit, the previous jobs will be canceled
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}

.github/workflows/chatbot_finetuning.yml

@@ -7,7 +7,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 jobs:
   call-finetune-mpt-7b-chat:
     uses: ./.github/workflows/chatbot-finetune-mpt-7b-chat.yml

.github/workflows/deploy-test.yml

@@ -7,7 +7,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 env:
   OUT_SCRIPT_PATH: ${{ github.workspace }}/.github/workflows/script/models
   SCRIPT_PATH: /intel-extension-for-transformers/.github/workflows/script

.github/workflows/format_scan.yml

@@ -11,7 +11,6 @@ on:
       - .github/workflows/format_scan.yml
       - .github/workflows/script/formatScan/**
   workflow_dispatch:
-permissions: write-all
 # If there is a new commit, the previous jobs will be canceled
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}

.github/workflows/llm-test.yml

@@ -13,7 +13,6 @@ on:
        - "!intel_extension_for_transformers/transformers/runtime/third_party/**"
        - "!intel_extension_for_transformers/transformers/runtime/docs/**"
   workflow_dispatch:
-permissions: write-all
 # If there is a new commit, the previous jobs will be canceled
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
@@ -50,6 +49,7 @@ jobs:
       - name: Binary build
         run: |
           cd ${{ github.workspace }}
+          source ~/.bashrc
           conda activate llm-test || source activate llm-test
           compiler_version=11.1.0
           conda install --update-deps -c conda-forge gxx==${compiler_version} gcc==${compiler_version} gxx_linux-64==${compiler_version} libstdcxx-ng sysroot_linux-64 libxcrypt -y

.github/workflows/optimize-test.yml

@@ -7,7 +7,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 env:
   OUT_SCRIPT_PATH: ${{ github.workspace }}/.github/workflows/script/models
   SCRIPT_PATH: /intel-extension-for-transformers/.github/workflows/script

.github/workflows/publish.yml

@@ -5,7 +5,6 @@ on:
     branches:
       - main
   workflow_dispatch:
-permissions: write-all
 jobs:
   build:
 

.github/workflows/scorecard.yml

@@ -0,0 +1,73 @@
+# This workflow uses actions that are not certified by GitHub. They are provided
+# by a third-party and are governed by separate terms of service, privacy
+# policy, and support documentation.
+
+name: Scorecard supply-chain security
+on:
+  # For Branch-Protection check. Only the default branch is supported. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#branch-protection
+  branch_protection_rule:
+  # To guarantee Maintained check is occasionally updated. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#maintained
+  schedule:
+    - cron: '25 5 * * 5'
+  push:
+    branches: [ "main" ]
+
+# Declare default permissions as read only.
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecard analysis
+    runs-on: ubuntu-latest
+    permissions:
+      # Needed to upload the results to code-scanning dashboard.
+      security-events: write
+      # Needed to publish results and get a badge (see publish_results below).
+      id-token: write
+      # Uncomment the permissions below if installing in a private repository.
+      # contents: read
+      # actions: read
+
+    steps:
+      - name: "Checkout code"
+        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+        with:
+          persist-credentials: false
+
+      - name: "Run analysis"
+        uses: ossf/scorecard-action@0864cf19026789058feabb7e87baa5f140aac736 # v2.3.1
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          # (Optional) "write" PAT token. Uncomment the `repo_token` line below if:
+          # - you want to enable the Branch-Protection check on a *public* repository, or
+          # - you are installing Scorecard on a *private* repository
+          # To create the PAT, follow the steps in https://github.com/ossf/scorecard-action?tab=readme-ov-file#authentication-with-fine-grained-pat-optional.
+          # repo_token: ${{ secrets.SCORECARD_TOKEN }}
+
+          # Public repositories:
+          #   - Publish results to OpenSSF REST API for easy access by consumers
+          #   - Allows the repository to include the Scorecard badge.
+          #   - See https://github.com/ossf/scorecard-action#publishing-results.
+          # For private repositories:
+          #   - `publish_results` will always be set to `false`, regardless
+          #     of the value entered here.
+          publish_results: true
+
+      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
+      # format to the repository Actions tab.
+      - name: "Upload artifact"
+        uses: actions/upload-artifact@97a0fba1372883ab732affbe8f94b823f91727db # v3.pre.node20
+        with:
+          name: SARIF file
+          path: results.sarif
+          retention-days: 5
+
+      # Upload the results to GitHub's code scanning dashboard (optional).
+      # Commenting out will disable upload of results to your repo's Code Scanning dashboard
+      - name: "Upload to code-scanning"
+        uses: github/codeql-action/upload-sarif@1b1aada464948af03b950897e5eb522f92603cc2 # v3.24.9
+        with:
+          sarif_file: results.sarif

.github/workflows/script/launch_llm.sh

@@ -23,7 +23,7 @@ function main() {
     fi
 
     # init conda
-    #. $(dirname ${CONDA_EXE})/../etc/profile.d/conda.sh
+    source ~/.bashrc
     conda activate $conda_env || source activate $conda_env
 
     # env

.github/workflows/script/models/run_llm.sh

@@ -36,17 +36,16 @@ main() {
 }
 
 function prepare() {
-    [[ -d ${HOME}/anaconda3/bin ]] && export PATH=${HOME}/anaconda3/bin/:$PATH
-    [[ -d ${HOME}/miniconda3/bin ]] && export PATH=${HOME}/miniconda3/bin/:$PATH
-    export LD_LIBRARY_PATH=/lib64/libcrypto.so.1.1:${HOME}/miniconda3/envs/${conda_env_name}/lib/:$LD_LIBRARY_PATH
+    source ~/.bashrc
+    source activate ${conda_env_name} || conda activate ${conda_env_name}
+    export LD_LIBRARY_PATH=/lib64/libcrypto.so.1.1:${CONDA_PREFIX}/lib/:$LD_LIBRARY_PATH
     if [[ ${precision} == "fp8" ]]; then
         export NE_WEIGHT_FP8_4E3M=1
     fi
     if [[ ${model} == "gpt-j-6b" ]]|| [[ model == "gpt-j-6b-pruned" ]]; then
         working_dir="${WORKING_DIR}/examples/huggingface/pytorch/text-generation/deployment"
     fi
     $BOLD_YELLOW && echo "Running ---- ${framework}, ${model}----Prepare"
-    source activate ${conda_env_name} || conda activate ${conda_env_name}
     if [[ ${cpu} == *"spr"* ]] || [[ ${cpu} == *"SPR"* ]] || [[ ${cpu} == *"Spr"* ]]; then
         export CC=/opt/rh/gcc-toolset-11/root/usr/bin/gcc
         export CXX=/opt/rh/gcc-toolset-11/root/usr/bin/g++
@@ -56,8 +55,7 @@ function prepare() {
     echo "Working in ${working_dir}"
     echo -e "\nInstalling model requirements..."
     export PATH=/lib64/libcrypto.so.1.1:$PATH
-    cp /lib64/libcrypto.so.1.1 ${HOME}/miniconda3/envs/${conda_env_name}/lib/libcrypto.so.1.1
-    cp /lib64/libcrypto.so.1.1 ${HOME}/miniconda3/lib/libcrypto.so.1.1
+    cp /lib64/libcrypto.so.1.1 ${CONDA_PREFIX}/lib/libcrypto.so.1.1
     if [ -f "requirements.txt" ]; then
         sed -i '/^transformers/d' requirements.txt
         n=0

.github/workflows/script/prepare_env_with_conda.sh

@@ -6,13 +6,6 @@ if [[ -z "${conda_env_name}" ]] || [[ -z "${python_version}" ]]; then
     exit 1
 fi
 
+source ~/.bashrc
 conda create -n ${conda_env_name} python=${python_version} -y
 source activate ${conda_env_name} || conda activate ${conda_env_name}
-#pip install -U pip
-#
-#if [ -f "requirements.txt" ]; then
-#    python -m pip install --default-timeout=100 -r requirements.txt
-#    pip list
-#else
-#    echo "Not found requirements.txt file."
-#fi

.github/workflows/sparse_lib_CI.yml

@@ -8,7 +8,6 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
-permissions: write-all
 
 env:
   DOCKER_CONFIG_NAME: "commonDockerConfig"

.github/workflows/trellix.yaml

@@ -3,7 +3,6 @@ name: Trellix Command Line Scanner
 on:
   workflow_dispatch:
 
-permissions: write-all
 jobs:
   Trellix:
     runs-on: inner-source

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

@@ -14,7 +14,6 @@ on:
       - "!intel_extension_for_transformers/transformers/runtime/third_party/**"
       - "!intel_extension_for_transformers/transformers/runtime/docs/**"
   workflow_dispatch:
-permissions: write-all
 # If there is a new commit, the previous jobs will be canceled
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}

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

@@ -14,7 +14,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 env:
   DOCKER_CONFIG_NAME: "commonDockerConfig"
   REPO_NAME: "intel-extension-for-transformers"

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

@@ -25,7 +25,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 env:
   DOCKER_CONFIG_NAME: "commonDockerConfig"
   REPO_NAME: "intel-extension-for-transformers"

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

@@ -12,7 +12,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 env:
   DOCKER_CONFIG_NAME: "commonDockerConfig"
   REPO_NAME: "intel-extension-for-transformers"

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

@@ -23,7 +23,6 @@ on:
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
-permissions: write-all
 env:
   DOCKER_CONFIG_NAME: "commonDockerConfig"
   REPO_NAME: "intel-extension-for-transformers"

.github/workflows/windows-test.yml

@@ -14,7 +14,6 @@ on:
       - "!intel_extension_for_transformers/transformers/runtime/test/**"
       - "!intel_extension_for_transformers/qbits/qbits_ut/**"
   workflow_dispatch:
-permissions: write-all
 # If there is a new commit, the previous jobs will be canceled
 concurrency:
     group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}

SECURITY.md

@@ -1,3 +1,8 @@
+OpenSSF Badge
+===============
+
+## [OpenSSF Badge](https://www.bestpractices.dev/en/projects/9128)
+
 Security Policy
 ===============
 

examples/huggingface/tensorflow/language-modeling/quantization/README.md

@@ -31,7 +31,7 @@ pip install -r requirements.txt
 
 ```
 cd ptq
-bash run_tuning.sh  --topology=[topology]
+bash run_tuning.sh --topology=[topology]
 ```
 
 * To benchmark the int8 model
@@ -52,12 +52,12 @@ bash run_benchmark.sh --topology=[topology] --mode=benchmark --int8=true
 
 ```
 cd ptq
-bash run_tuning.sh  --topology=[topology]
+bash run_tuning.sh --topology=[topology]
 ```
 
 * To benchmark the int8 model
 
 ```
 cd ptq
 bash run_benchmark.sh --topology=[topology] --mode=benchmark --int8=true
-```
+```

requirements.txt

@@ -1,3 +1,3 @@
 py-cpuinfo
-setuptools>=65
+setuptools==69.5.1
 setuptools_scm[toml]>=6.2