fix

.github/workflows/offline_inference.yml

@@ -0,0 +1,32 @@
+name: OFFLINE_INFERENCE
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+    branches:
+    - main
+
+jobs:
+  cancel_previous_workflows:
+    runs-on: [self-hosted]
+    timeout-minutes: 3
+    steps:
+    - uses: styfle/[email protected]
+      with:
+        all_but_latest: true
+
+  offline_inference:
+    needs: cancel_previous_workflows
+    runs-on: [self-hosted]
+    timeout-minutes: 10
+    steps:
+    - uses: actions/checkout@v4
+    - name: Run offline inference example
+      run: |
+        nvidia-docker run --rm -t --net host --ipc host \
+          -v ${PWD}:/workspace \
+          -w /workspace \
+          registry.cn-beijing.aliyuncs.com/llumnix/llumnix-dev:20240909_action_678a439 \
+          bash -c "pip install -e . > /dev/null && python examlpes/offline_inference.py"