glm53-flash-aiden image: bump base to production-1.2 (fused mHC prefill kernel, 1.37x mHC section @4K tokens per aiden; VLLM_MHC_FUSED_LARGE=0 to revert)

docker-images/glm53-flash-aiden/Dockerfile

@@ -1,3 +1,3 @@
-FROM aidendle94/sparkrun-vllm-glm53-gb10:production-1.1
+FROM aidendle94/sparkrun-vllm-glm53-gb10:production-1.2
 
 RUN pip install --no-cache-dir --no-deps --force-reinstall instanttensor==0.1.9