add GitHub CI for Intel GPU (#536)

## Summary
This PR adds the dependencies for using liger-kernel on XPU and adds the
workflow.yml.

## Testing Done
Test done on local XPU machine. To make all tests pass, we need to first
merge PR #535 first.

- Hardware Type: Intel(R) Data Center GPU Max 1550
- [x] run `make test` to ensure correctness
- [x] run `make checkstyle` to ensure code style
- [x] run `make test-convergence` to ensure convergence

---------

Co-authored-by: Byron Hsu <[email protected]>
Co-authored-by: Stefan He <[email protected]>

Author: 3 people

.github/workflows/intel-ci.yml

@@ -0,0 +1,71 @@
+name: Intel GPU
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "src/**"
+      - "test/**"
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "src/**"
+      - "test/**"
+  schedule:
+    # Runs at 00:00 UTC daily
+    - cron: '0 0 * * *'
+  workflow_dispatch:  # Enables manual trigger
+
+concurrency:
+  # This causes it to cancel previous in-progress actions on the same PR / branch,
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  checkstyle:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.10'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r dev/fmt-requirements.txt
+
+    - name: Run checkstyle
+      run: make checkstyle
+
+  tests:
+    runs-on: linux-max1550-gpu-8
+    needs: [checkstyle]
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.10'
+
+    - name: Setup Dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e .[dev] --extra-index-url https://download.pytorch.org/whl/test/xpu
+    
+    - name: List Python Environments
+      run: python -m pip list
+    
+    - name: Run Unit Tests
+      run: |
+        make test
+        make test-convergence

setup.py

@@ -21,6 +21,11 @@ def get_default_dependencies():
             "torch>=2.6.0.dev",
             "triton>=3.0.0",
         ]
+    elif platform == "xpu":
+        return [
+            "torch>=2.6.0",
+            "pytorch-triton-xpu>=3.2.0",
+        ]
 
 
 def get_optional_dependencies():
@@ -43,8 +48,7 @@ def get_optional_dependencies():
     }
 
 
-# TODO: add intel XPU
-def get_platform() -> Literal["cuda", "rocm", "cpu"]:
+def get_platform() -> Literal["cuda", "rocm", "cpu", "xpu"]:
     """
     Detect whether the system has NVIDIA or AMD GPU without torch dependency.
     """
@@ -60,8 +64,13 @@ def get_platform() -> Literal["cuda", "rocm", "cpu"]:
             print("ROCm GPU detected")
             return "rocm"
         except (subprocess.SubprocessError, FileNotFoundError):
-            print("No GPU detected")
-            return "cpu"
+            try:
+                subprocess.run(["xpu-smi"], check=True)
+                print("Intel GPU detected")
+                return "xpu"
+            except (subprocess.SubprocessError, FileNotFoundError):
+                print("No GPU detected")
+                return "cpu"
 
 
 setup(