kindling recipes: docker_image_dir=glm53-kindling (shared build context for all 3 TP variants)

recipes/glm53-kindling-2x/recipe.toml

@@ -26,6 +26,8 @@
 engine = "vllm"
 name = "GLM-5.3-Flash NVFP4 (kindlingai gx10 stack, 2x, DFlash2)"
 docker_image = "spark-glm53:v9"
+# shared image build dir (all three TP variants build the same image)
+docker_image_dir = "glm53-kindling"
 entrypoint = ["vllm", "serve"]
 model = "/root/.cache/huggingface/hub/models--nvidia--GLM-5.3-Flash-NVFP4/snapshots/da920bb0b9f4a06727223a349e55468e38352348"
 parent_model = "nvidia/GLM-5.3-Flash-NVFP4"

recipes/glm53-kindling-4x/recipe.toml

@@ -23,6 +23,8 @@
 engine = "vllm"
 name = "GLM-5.3-Flash NVFP4 (kindlingai gx10 stack, 4x, DFlash2)"
 docker_image = "spark-glm53:v9"
+# shared image build dir (all three TP variants build the same image)
+docker_image_dir = "glm53-kindling"
 entrypoint = ["vllm", "serve"]
 model = "/root/.cache/huggingface/hub/models--nvidia--GLM-5.3-Flash-NVFP4/snapshots/da920bb0b9f4a06727223a349e55468e38352348"
 parent_model = "nvidia/GLM-5.3-Flash-NVFP4"

recipes/glm53-kindling-6x/recipe.toml

@@ -32,6 +32,8 @@
 engine = "vllm"
 name = "GLM-5.3-Flash NVFP4 (kindlingai gx10 stack, 6x, DFlash2)"
 docker_image = "spark-glm53:v9"
+# shared image build dir (all three TP variants build the same image)
+docker_image_dir = "glm53-kindling"
 entrypoint = ["vllm", "serve"]
 model = "/root/.cache/huggingface/glm-5.3-flash-nvfp4-tp6pad"
 parent_model = "nvidia/GLM-5.3-Flash-NVFP4"