[iluvatar][CI] refactor iluvatar_ci (#5588)

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* refactor iluvatar_ci

* Update Docker image tag in iluvatar_test workflow

* Update default Docker image version in workflow

* Update iluvatar_test.yml

* Update default Docker image in workflow config

* Update model path in run_ernie300B_4layer.py

* Update model path in offline inference check

* Add model_data directory and copy model files

Create model_data directory and copy necessary files.

* Update run_ernie_vl_28B.py

* Update run_ernie300B_4layer.py

* Update paddlepaddle installation method in script

* Change wget command to include proxy option

* Modify paddle package installation in CI script

Updated installation commands for paddle packages.

* Update paddlepaddle and paddle-iluvatar-gpu versions

* Delete .github/workflows/ci_iluvatar.yml

* Rename workflow from ILUVATAR Test to ILUVATAR-CI

* Update installation commands for paddlepaddle and iluvatar

.github/workflows/_iluvatar_cases.yml

@@ -0,0 +1,70 @@
+name: ILUVATAR-Test
+
+on:
+  workflow_call:
+    inputs:
+      DOCKER_IMAGE:
+        description: "Build Images"
+        required: true
+        type: string
+        default: "ccr-2vdh3abv-pub.cnc.bj.baidubce.com/device/paddle-ixuca:fd-ci"
+      FASTDEPLOY_ARCHIVE_URL:
+        description: "URL of the compressed FastDeploy code archive."
+        required: true
+        type: string
+      CACHE_DIR:
+        description: "Cache Dir Use"
+        required: false
+        type: string
+        default: ""
+      MODEL_CACHE_DIR:
+        description: "Cache Dir Use"
+        required: false
+        type: string
+        default: ""
+
+jobs:
+  run_iluvatar_cases:
+    runs-on: iluvatar-gpu-2
+    timeout-minutes: 60
+    container:
+      image: ${{ inputs.DOCKER_IMAGE }}
+      env:
+        LD_LIBRARY_PATH: /usr/local/corex/lib
+        LIBRARY_PATH: /usr/local/corex/lib
+    steps:
+      - name: Print current runner name
+        run: |
+          echo "Current runner name: ${{ runner.name }}"
+      - name: Code Prepare
+        shell: bash
+        env:
+          docker_image: ${{ inputs.DOCKER_IMAGE }}
+          fd_archive_url: ${{ inputs.FASTDEPLOY_ARCHIVE_URL }}
+        run: |
+            set -x
+            REPO="https://github.com/${{ github.repository }}.git"
+            FULL_REPO="${{ github.repository }}"
+            REPO_NAME="${FULL_REPO##*/}"
+            BASE_BRANCH="${{ github.base_ref }}"
+            # Clean the repository directory before starting
+            if [ -d ${REPO_NAME} ]; then
+              echo "Directory ${REPO_NAME} exists, removing it..."
+              rm -rf ${REPO_NAME}*
+            fi
+            git config --global --add safe.directory '*'
+            wget -q ${fd_archive_url}
+            tar -xf FastDeploy.tar.gz
+            rm -rf FastDeploy.tar.gz
+            cd FastDeploy
+            git config --global user.name "FastDeployCI"
+            git config --global user.email "fastdeploy_ci@example.com"
+            git log -n 3 --oneline
+
+      - name: Run CI unittest
+        env:
+          CACHE_DIR: ${{ inputs.CACHE_DIR }}
+          MODEL_CACHE_DIR: ${{ inputs.MODEL_CACHE_DIR }}
+        run: |
+          cd FastDeploy
+          bash scripts/run_ci_iluvatar.sh

.github/workflows/ci_iluvatar.yml

@@ -1,88 +1,23 @@
-name: CI_ILUVATAR
-
+name: ILUVATAR-CI
 on:
   pull_request:
-    branches: [ develop ]
-  workflow_dispatch:
+    types: [opened, synchronize]
+    branches: [develop, release/**]
+permissions: read-all
 
 concurrency:
-  group: ${{ github.event.pull_request.number }}-iluvatar-ci
+  group: ${{ github.event.pull_request.number }}-${{ github.workflow }}
   cancel-in-progress: true
 
 jobs:
-  CI_ILUVATAR:
-    runs-on: [self-hosted, ILUVATAR_8Card]
-    steps:
-      - name: Print current runner name
-        run: |
-          echo "Current runner name: ${{ runner.name }}"
-      # Because the system version is lower than 2.23, the checkout cannot be used.
-      # - name: Checkout code
-      #   uses: actions/checkout@v4
+  clone:
+    name: FD-Clone-Linux
+    uses: ./.github/workflows/_clone_linux.yml
 
-      - name: Code Checkout
-        env:
-          docker_image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/device/paddle-ixuca:paddle-ocr-vl-1107
-        run: |
-          REPO="https://github.com/${{ github.repository }}.git"
-          FULL_REPO="${{ github.repository }}"
-          REPO_NAME="${FULL_REPO##*/}"
-          BASE_BRANCH="${{ github.base_ref }}"
-          # Clean the repository directory before starting
-          docker run --rm --net=host -v $(pwd):/workspace -w /workspace \
-          -e "REPO_NAME=${REPO_NAME}" \
-          -e "BASE_BRANCH=${BASE_BRANCH}" \
-          ${docker_image} /bin/bash -c '
-            if [ -d ${REPO_NAME} ]; then
-              echo "Directory ${REPO_NAME} exists, removing it..."
-              rm -rf ${REPO_NAME}
-            fi
-          '
-          git config --global http.proxy "http://61.151.249.150:33128"
-          git config --global https.proxy "http://61.151.249.150:33128"
-          git config --global user.name "FastDeployCI"
-          git config --global user.email "fastdeploy_ci@example.com"
-          git clone --recursive ${REPO} ${REPO_NAME} -b ${BASE_BRANCH}
-          cd FastDeploy
-          if [ "${{ github.event_name }}" = "pull_request" ]; then
-            git fetch origin pull/${{ github.event.pull_request.number }}/head:pr/${{ github.event.pull_request.number }}
-            git merge pr/${{ github.event.pull_request.number }}
-            git log -n 3 --oneline
-          else
-            git checkout ${{ github.sha }}
-            git log -n 3 --oneline
-          fi
-
-      - name: Run CI unittest
-        env:
-          docker_image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/device/paddle-ixuca:paddle-ocr-vl-1107
-        run: |
-          runner_name="${{ runner.name }}"
-          last_char="${runner_name: -1}"
-
-          if [[ "$last_char" =~ [0-3] ]]; then
-            gpu_id="$last_char"
-          else
-            gpu_id="0"
-          fi
-          FD_API_PORT=$((9180 + gpu_id * 100))
-          FD_ENGINE_QUEUE_PORT=$((9150 + gpu_id * 100))
-          FD_METRICS_PORT=$((9170 + gpu_id * 100))
-
-          PARENT_DIR=$(dirname "$WORKSPACE")
-          echo "PARENT_DIR:$PARENT_DIR"
-          docker run --rm --net=host --pid=host --cap-add=ALL --privileged --shm-size=64G  \
-          -v /usr/src:/usr/src -v /lib/modules:/lib/modules -v /dev:/dev \
-          -v $(pwd):/workspace -w /workspace \
-          -v "/data1/fastdeploy:/data1/fastdeploy" \
-          -e "MODEL_PATH=/ssd3/model" \
-          -e "http_proxy=$(git config --global --get http.proxy)" \
-          -e "https_proxy=$(git config --global --get https.proxy)" \
-          -e "FD_API_PORT=${FD_API_PORT}" \
-          -e "FD_ENGINE_QUEUE_PORT=${FD_ENGINE_QUEUE_PORT}" \
-          -e "FD_METRICS_PORT=${FD_METRICS_PORT}" \
-           ${docker_image} /bin/bash -c "
-          git config --global --add safe.directory /workspace/FastDeploy
-          cd FastDeploy
-          bash scripts/run_ci_iluvatar.sh
-          "
+  iluvatar_test:
+    name: Run iluvatar Tests
+    needs: [clone]
+    uses: ./.github/workflows/_iluvatar_cases.yml
+    with:
+      DOCKER_IMAGE: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/device/paddle-ixuca:fd-ci
+      FASTDEPLOY_ARCHIVE_URL: ${{ needs.clone.outputs.repo_archive_url }}

scripts/run_ci_iluvatar.sh

@@ -14,8 +14,13 @@ ln -sf /usr/local/bin/python3 /usr/local/bin/python
 echo "pip requirements"
 python -m pip install -r requirements_iluvatar.txt
 echo "install paddle cpu and custom device"
-python -m pip install paddlepaddle==3.3.0.dev20251103 -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
-python -m pip install paddle-iluvatar-gpu==3.0.0.dev20251107 -i https://www.paddlepaddle.org.cn/packages/nightly/ixuca/
+python -m pip install  --pre paddlepaddle -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
+python -m pip install --pre paddle-iluvatar-gpu -i https://www.paddlepaddle.org.cn/packages/nightly/ixuca/
+#python -m pip install paddlepaddle==3.3.0.dev20251219 -i https://www.paddlepaddle.org.cn/packages/nightly/cpu/
+#python -m pip install paddle-iluvatar-gpu==3.0.0.dev20251223 -i https://www.paddlepaddle.org.cn/packages/nightly/ixuca/
+mkdir -p /model_data/
+cp -r /aistudio/paddle_ci/ERNIE_300B_4L/ /model_data/
+cp -r /aistudio/paddle_ci/ERNIE-4.5-VL-28B-A3B-Paddle /model_data/
 echo "build whl"
 bash build.sh || exit 1
 

tests/ci_use/iluvatar_UT/run_ernie300B_4layer.py

@@ -33,7 +33,7 @@ def offline_infer_check():
     ]
     sampling_params = SamplingParams(temperature=0.8, top_p=0.00001, max_tokens=16)
     llm = LLM(
-        model="/data1/fastdeploy/ERNIE_300B_4L",
+        model="/model_data/ERNIE_300B_4L",
         tensor_parallel_size=2,
         max_model_len=8192,
         quantization="wint8",

tests/ci_use/iluvatar_UT/run_ernie_vl_28B.py

@@ -33,7 +33,7 @@ from ci_use.iluvatar_UT.utils import TIMEOUT_MSG, timeout
 def offline_infer_check():
     set_random_seed(123)
 
-    PATH = "/data1/fastdeploy/ERNIE-4.5-VL-28B-A3B-Paddle"
+    PATH = "/model_data/ERNIE-4.5-VL-28B-A3B-Paddle"
     tokenizer = Ernie4_5Tokenizer.from_pretrained(PATH)
 
     messages = [