show logs

Author: anakin87

.github/workflows/vllm.yml

@@ -85,17 +85,16 @@ jobs:
         env:
           VLLM_CPU_KVCACHE_SPACE: "4"
         run: |
-          hatch run -- nohup vllm serve ${{ env.VLLM_MODEL }} \
+          nohup hatch run -- vllm serve ${{ env.VLLM_MODEL }} \
             --reasoning-parser qwen3 \
             --max-model-len 1024 \
             --enforce-eager \
             --dtype bfloat16 \
             --enable-auto-tool-choice \
-            --tool-call-parser hermes \
-            > vllm.log 2>&1 &
+            --tool-call-parser hermes &
 
-          # Wait for the vLLM server to be ready with a timeout of 300 seconds
-          timeout=300
+          # Wait for the vLLM server to be ready with a timeout of 600 seconds
+          timeout=600
           while [ $timeout -gt 0 ] && ! curl -sSf http://localhost:8000/health > /dev/null 2>&1; do
             echo "Waiting for vLLM server to start..."
             sleep 10
@@ -104,7 +103,6 @@ jobs:
 
           if [ $timeout -eq 0 ]; then
             echo "Timed out waiting for vLLM server to start."
-            cat vllm.log
             exit 1
           fi