Serve command: match validated recipe (--language-model-only)

README.md

@@ -100,6 +100,7 @@ The repo ships vLLM-ready weights (LoRA merged, keys repacked, Qwen3.5-9B text c
 vllm serve ZelligeAI/tessera-preview-9b \
   --served-model-name tessera-preview-9b \
   --max-model-len 32768 --dtype bfloat16 \
+  --language-model-only --gpu-memory-utilization 0.90 \
   --reasoning-parser qwen3 \
   --enable-auto-tool-choice --tool-call-parser qwen3_coder
 ```