Update ci workflows (#1804)

.github/workflows/deploy-docs.yml

@@ -1,20 +1,15 @@
 name: Build Documentation
 
 on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
   workflow_dispatch:
 
 jobs:
   execute-notebooks:
     runs-on: 1-gpu-runner
-    if: github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch'
+    if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
     steps:
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
+      - name: Checkout code
+        uses: actions/checkout@v3
 
       - name: Set up Python
         uses: actions/setup-python@v4
@@ -23,22 +18,14 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
+          bash scripts/ci_install_dependency.sh
           pip install -r docs/requirements.txt
-          pip install nbconvert jupyter_client ipykernel ipywidgets matplotlib
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
 
       - name: Setup Jupyter Kernel
         run: |
           python -m ipykernel install --user --name python3 --display-name "Python 3"
 
       - name: Execute notebooks
-        env:
-          HF_HOME: /hf_home
-          SGLANG_IS_IN_CI: true
-          CUDA_VISIBLE_DEVICES: 0
         run: |
           cd docs/en
           for nb in *.ipynb; do
@@ -54,34 +41,18 @@ jobs:
     if: github.event_name == 'push' && github.ref == 'refs/heads/main'
     runs-on: 1-gpu-runner
     steps:
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
+      - name: Checkout code
+        uses: actions/checkout@v3
 
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
           python-version: '3.9'
 
-      - name: Cache Python dependencies
-        uses: actions/cache@v3
-        with:
-          path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-
-
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
+          bash scripts/ci_install_dependency.sh
           pip install -r docs/requirements.txt
-          pip install nbconvert jupyter_client ipykernel ipywidgets matplotlib
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
-
-      - name: Install Pandoc
-        run: |
           apt-get update
           apt-get install -y pandoc
 

.github/workflows/lint.yml

@@ -8,10 +8,10 @@ jobs:
     steps:
       - uses: actions/checkout@v2
 
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
+      - name: Set up Python
+        uses: actions/setup-python@v4
         with:
-          python-version: 3.9
+          python-version: '3.9'
 
       - name: Install pre-commit hook
         run: |

.github/workflows/nightly-eval.yml

@@ -24,9 +24,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Nightly gsm8k Accuracy
         timeout-minutes: 60

.github/workflows/pr-test.yml

@@ -27,10 +27,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[dev]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Run test
         timeout-minutes: 10
@@ -47,10 +44,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[dev]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Run test
         timeout-minutes: 20
@@ -67,10 +61,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[dev]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Run test
         timeout-minutes: 20
@@ -87,10 +78,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[dev]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Run test
         timeout-minutes: 20
@@ -107,10 +95,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[dev]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Run test
         timeout-minutes: 20
@@ -127,10 +112,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Benchmark Single Latency
         timeout-minutes: 10
@@ -165,10 +147,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Benchmark Offline Throughput (w/o RadixAttention)
         timeout-minutes: 10
@@ -197,10 +176,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
       - name: Benchmark Offline Throughput (TP=2)
         timeout-minutes: 10
@@ -229,10 +205,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
           git clone https://github.com/merrymercy/human-eval.git
           cd human-eval
@@ -253,10 +226,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          pip install --upgrade pip
-          pip install -e "python[all]"
-          pip install transformers==4.45.2
-          pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+          bash scripts/ci_install_dependency.sh
 
           git clone https://github.com/merrymercy/human-eval.git
           cd human-eval

.github/workflows/release-github.yml

@@ -1,25 +0,0 @@
-name: Release GitHub
-on:
-  workflow_dispatch:
-jobs:
-  publish:
-    if: github.repository == 'sgl-project/sglang'
-    runs-on: ubuntu-latest
-    environment: 'prod'
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-      
-      - name: Get version
-        id: get_version
-        run: |
-          version=$(cat python/sglang/version.py | cut -d'"' -f2)
-          echo "TAG=v$version" >> $GITHUB_OUTPUT
-
-      - name: Release
-        uses: softprops/action-gh-release@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.REPO_TOKEN }}
-        with:
-          name: Release ${{ steps.get_version.outputs.TAG }}
-          tag_name: ${{ steps.get_version.outputs.TAG }}

.github/workflows/release-pypi.yml

@@ -13,12 +13,14 @@ jobs:
     runs-on: ubuntu-latest
     environment: 'prod'
     steps:
-      - name: Set up python3.8
+      - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.8'
+          python-version: '3.9'
+
       - name: Checkout repository
         uses: actions/checkout@v3
+
       - name: Upload to pypi
         run: |
           cd python