Unified Gemma 4 family image for Gemma-4-31B and GEV-26B-Decide

- detect_model.py picks TP/port/served name/eager/util from config.json
- validate TP against the model config (dense global KV heads, MoE k % 32)
- one apply_patch.py covers both variants, idempotent
- Dockerfile stays generic: no ENV/WORKDIR/EXPOSE/ENTRYPOINT
- run.sh/verify.sh follow the llama4-bi150 layout

.dockerignore

@@ -0,0 +1,7 @@
+.git
+.gitea
+README.md
+run.sh
+verify.sh
+docker-compose.yml
+*.log