Initial production-ready Gemma 3 vLLM ROCm stack

Co-Authored-By: Oz <oz-agent@warp.dev>

scripts/test_api.sh

@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+# Tests local vLLM OpenAI-compatible API using curl and validates response shape.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "${SCRIPT_DIR}/.." && pwd)"
+ENV_FILE="${REPO_ROOT}/.env"
+
+if [[ ! -f "${ENV_FILE}" ]]; then
+  echo "[test_api][error] .env file not found. Copy .env.example to .env first." >&2
+  exit 1
+fi
+
+# shellcheck disable=SC1090
+source "${ENV_FILE}"
+
+BACKEND_PORT="${BACKEND_PORT:-8000}"
+GEMMA_MODEL_ID="${GEMMA_MODEL_ID:-google/gemma-3-1b-it}"
+VLLM_API_KEY="${VLLM_API_KEY:-EMPTY}"
+API_URL="http://localhost:${BACKEND_PORT}/v1/chat/completions"
+
+payload_file="$(mktemp)"
+response_file="$(mktemp)"
+trap 'rm -f "${payload_file}" "${response_file}"' EXIT
+
+cat > "${payload_file}" <<JSON
+{
+  "model": "${GEMMA_MODEL_ID}",
+  "messages": [
+    {"role": "system", "content": "You are a concise assistant."},
+    {"role": "user", "content": "Say hello from Gemma 3 running on vLLM."}
+  ],
+  "temperature": 0.2,
+  "max_tokens": 64
+}
+JSON
+
+http_status="$(curl -sS -o "${response_file}" -w '%{http_code}'   -H "Content-Type: application/json"   -H "Authorization: Bearer ${VLLM_API_KEY}"   -X POST "${API_URL}"   --data @"${payload_file}")"
+
+if [[ ! "${http_status}" =~ ^2 ]]; then
+  echo "[test_api][error] API returned HTTP ${http_status}" >&2
+  cat "${response_file}" >&2
+  echo "[test_api][hint] See docs/TROUBLESHOOTING.md#vllm-container-exits-or-fails-healthchecks" >&2
+  exit 1
+fi
+
+if ! grep -q '"choices"' "${response_file}"; then
+  echo "[test_api][error] API response did not include expected 'choices' field." >&2
+  cat "${response_file}" >&2
+  exit 1
+fi
+
+echo "[test_api] Success. API responded with expected structure."
+cat "${response_file}"