fix: modify VLLM_URL for containerized environments

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>

Author: nathan-weinberg

.github/actions/setup-vllm/action.yml

@@ -12,6 +12,7 @@ runs:
           --name vllm \
           -p 8000:8000 \
           --privileged=true \
+          --net=host \
           quay.io/higginsd/vllm-cpu:65393ee064 \
           --host 0.0.0.0 \
           --port 8000 \

.github/workflows/redhat-distro-container.yml

@@ -60,6 +60,7 @@ jobs:
         shell: bash
         env:
           INFERENCE_MODEL: meta-llama/Llama-3.2-1B-Instruct
+          VLLM_URL: http://localhost:8000/v1
         run: ./tests/smoke.sh
 
       - name: Log in to Quay.io

tests/smoke.sh

@@ -7,8 +7,10 @@ function start_and_wait_for_llama_stack_container {
   docker run \
     -d \
     --pull=never \
+    --net=host \
     -p 8321:8321 \
     --env INFERENCE_MODEL="$INFERENCE_MODEL" \
+    --env VLLM_URL="$VLLM_URL" \
     --env TRUSTYAI_LMEVAL_USE_K8S=False \
     --env TRUSTYAI_LM_EVAL_NAMESPACE=dummy \
     --name llama-stack \