Update CI workflows (#1210)

.github/workflows/accuracy-test.yml

@@ -20,7 +20,7 @@ concurrency:
 jobs:
   accuracy-test:
     if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
-    runs-on: accuracy
+    runs-on: accuracy-test
 
     steps:
     - name: Checkout code
@@ -28,9 +28,6 @@ jobs:
 
     - name: Install dependencies
       run: |
-        source $HOME/venv/bin/activate
-        echo "$HOME/venv/bin" >> $GITHUB_PATH
-
         pip install --upgrade pip
         pip install -e "python[all]"
         pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
@@ -40,7 +37,7 @@ jobs:
         pip install -e .
 
     - name: Evaluate Accuracy
+      timeout-minutes: 20
       run: |
         cd test/srt
         python3 test_eval_accuracy_large.py
-      timeout-minutes: 20

.github/workflows/e2e-test.yml

@@ -20,7 +20,7 @@ concurrency:
 jobs:
   e2e-test:
     if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
-    runs-on: e2e
+    runs-on: e2e-test
 
     steps:
     - name: Checkout code
@@ -28,27 +28,24 @@ jobs:
 
     - name: Install dependencies
       run: |
-        source $HOME/venv/bin/activate
-        echo "$HOME/venv/bin" >> $GITHUB_PATH
-
         pip install --upgrade pip
         pip install -e "python[all]"
         pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
 
     - name: Benchmark Serving Throughput
+      timeout-minutes: 10
       run: |
         cd test/srt
         python3 -m unittest test_serving_throughput.TestServingThroughput.test_default
-      timeout-minutes: 10
 
     - name: Benchmark Serving Throughput (w/o RadixAttention)
+      timeout-minutes: 10
       run: |
         cd test/srt
         python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_radix_cache
-      timeout-minutes: 10
 
     - name: Benchmark Serving Throughput (w/o ChunkedPrefill)
+      timeout-minutes: 10
       run: |
         cd test/srt
         python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_chunked_prefill
-      timeout-minutes: 10

.github/workflows/moe-test.yml

@@ -18,30 +18,28 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-    moe-test:
-        if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
-        runs-on: accuracy
-    
-        steps:
-            - name: Checkout code
-              uses: actions/checkout@v3
-        
-            - name: Install dependencies
-              run: |
-                source $HOME/venv/bin/activate
-                echo "$HOME/venv/bin" >> $GITHUB_PATH
-        
-                pip install --upgrade pip
-                pip install -e "python[all]"
-                pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
+  moe-test:
+    if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
+    runs-on: moe-test
 
-            - name: Benchmark MOE Serving Throughput
-              uses: nick-fields/retry@v3
-              with:
-                timeout_minutes: 15
-                max_attempts: 2
-                retry_on: error
-                command: |
-                  cd test/srt
-                  python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default
-                  python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default_without_radix_cache
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+
+    - 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
+
+    - name: Benchmark MoE Serving Throughput
+      timeout_minutes: 10
+      run: |
+        cd test/srt
+        python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default
+
+    - name: Benchmark MoE Serving Throughput (w/o RadixAttention)
+      timeout_minutes: 10
+      run: |
+        cd test/srt
+        python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default_without_radix_cache

.github/workflows/unit-test.yml

@@ -20,7 +20,7 @@ concurrency:
 jobs:
   unit-test:
     if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
-    runs-on: unit
+    runs-on: unit-test
 
     steps:
     - name: Checkout code
@@ -28,9 +28,6 @@ jobs:
 
     - name: Install dependencies
       run: |
-        source $HOME/venv/bin/activate
-        echo "$HOME/venv/bin" >> $GITHUB_PATH
-
         pip install --upgrade pip
         pip install -e "python[all]"
         pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
@@ -38,13 +35,13 @@ jobs:
         pip install sentence_transformers
 
     - name: Test Backend Runtime
+      timeout-minutes: 20
       run: |
         cd test/srt
         python3 run_suite.py --suite minimal
-      timeout-minutes: 20
 
     - name: Test Frontend Language
+      timeout-minutes: 10
       run: |
         cd test/lang
         python3 run_suite.py --suite minimal
-      timeout-minutes: 10