modal/omni: PRODUCTION DEPLOY - text inference fully verified, llama-server running on T4

- Chinese: 1.0s, '你好，我是MiniCPM系列模型...' (finish_reason=stop)
- English: 1.8s, 'The capital of France is Paris.' (finish_reason=stop)
- Cold start: 11s model load on T4
- --jinja flag confirmed working for correct chat template
- Production URL: https://andrew-jiabin--prego-pal-minicpm-omni-serve.modal.run

Next: add omni voice endpoints (prefill/generate/break) for full-duplex audio

docs/README_modal_deploy.md

@@ -110,7 +110,9 @@ modal run --detach -m modal_deploy.deploy_omni::test_inference
 
 ### Test Results (2026-06-11, T4)
 
-**Status**: llama-server fully operational on T4.
+**Status**: ✅ Deployed to production on T4.
+
+**Production URL**: `https://andrew-jiabin--prego-pal-minicpm-omni-serve.modal.run`
 
 | Metric | Value |
 |--------|-------|