SGL Backend

.github/workflows/coverage.yml

@@ -9,7 +9,7 @@ on:
 
 
 jobs:
-  test_coverage:
+  test_vllm_coverage:
     runs-on: ParallelHoss
 
     steps:
@@ -25,12 +25,45 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install -U pip
-          pip install -e .
+          pip install -e .[vllm]
           pip install -r requirements-dev.txt
 
       - name: Run tests
         run: |
-          coverage run --source=genlm/backend -m pytest --benchmark-disable --ignore=tests/test_mlx.py
+          coverage run --source=genlm/backend -m pytest --benchmark-disable --ignore=tests/test_mlx.py --ignore=tests/test_sgl.py
+          coverage json --omit "*/test*"
+          coverage report --omit "*/test*"
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          fail_ci_if_error: false
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: ./coverage.json
+          slug: genlm/genlm-backend
+
+  test_sgl_coverage:
+    runs-on: ParallelHoss
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - uses: actions/setup-python@v4
+        with:
+          python-version: 3.11.5
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install -U pip
+          pip install -e .[sgl]
+          pip install -r requirements-dev.txt
+
+      - name: Run tests
+        run: |
+          coverage run --source=genlm/backend -m pytest tests/test_sgl.py
           coverage json --omit "*/test*"
           coverage report --omit "*/test*"
 

.github/workflows/pytest.yml

@@ -23,6 +23,17 @@ jobs:
           python-version: 3.11.5
           cache: 'pip'
 
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@v1.3.1
+        with:
+          tool-cache: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: true
+          swap-storage: false
+
       - name: Install dependencies
         run: |
           python -m pip install -U pip

genlm/backend/llm/__init__.py

@@ -2,6 +2,7 @@
 from genlm.backend.llm.hf import AsyncTransformer
 from genlm.backend.llm.base import AsyncLM, MockAsyncLM
 from genlm.backend.llm.mlx import AsyncMlxLM
+from genlm.backend.llm.sgl import AsyncSGLTransformer
 
 import torch
 
@@ -36,6 +37,8 @@ def load_model_by_name(name, backend=None, llm_opts=None):
         return MockAsyncLM.from_name(name, **llm_opts)
     elif backend == "mlx":
         return AsyncMlxLM.from_name(name, **llm_opts)
+    elif backend == "sgl":
+        return AsyncSGLTransformer.from_name(name, **llm_opts)
     else:
         raise ValueError(f"Invalid backend: {backend}")
 
@@ -46,5 +49,6 @@ def load_model_by_name(name, backend=None, llm_opts=None):
     "AsyncVirtualLM",
     "AsyncTransformer",
     "AsyncMlxLM",
+    "AsyncSGLTransformer",
     "MockAsyncLM",
 ]