Initial production-ready Gemma 3 vLLM ROCm stack

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

backend/Dockerfile

@@ -0,0 +1,4 @@
+# Optional backend Dockerfile.
+# This stack uses the official vLLM ROCm image directly from docker-compose.yml.
+# Keep this file for future customizations.
+FROM vllm/vllm-openai-rocm:latest

backend/config/model.env.example

@@ -0,0 +1,7 @@
+HF_TOKEN=YOUR_HF_TOKEN_HERE
+VLLM_API_KEY=YOUR_LOCAL_API_KEY_HERE
+GEMMA_MODEL_ID=google/gemma-3-1b-it
+BACKEND_PORT=8000
+HUGGINGFACE_CACHE_DIR=/home/${USER}/.cache/huggingface
+VLLM_MAX_MODEL_LEN=4096
+VLLM_GPU_MEMORY_UTILIZATION=0.88