services: h3-blackwell-runtime: build: context: . dockerfile: Dockerfile.spark image: h3-blackwell-runtime:dev gpus: all volumes: - /home/daniel/aeon-spark-test/h3/comfy-models/diffusion_models:/models:ro - /home/daniel/aeon-spark-test/h3/comfy-models/text_encoders:/text-encoders:ro - /home/daniel/aeon-spark-test/h3/comfy-models/vae:/vae:ro - /home/daniel/aeon-spark-test/h3/h3-blackwell-runtime/artifacts:/artifacts:ro - /home/daniel/aeon-spark-test/h3/models/MiniMax-H3-Turbo-FL2VA/latest:/turbo:ro - /home/daniel/aeon-spark-test/h3/models/Minimax-H3-Latent-Upscaler:/latent-upscaler:ro - /home/daniel/StoryStudioAssets/H3-output:/output command: ["sleep", "infinity"] h3-hot-runtime: build: context: . dockerfile: Dockerfile.spark image: h3-blackwell-runtime:dev gpus: all volumes: - /home/daniel/aeon-spark-test/h3/comfy-models/diffusion_models:/models:ro - /home/daniel/aeon-spark-test/h3/comfy-models/text_encoders:/text-encoders:ro - /home/daniel/aeon-spark-test/h3/comfy-models/vae:/vae:ro - /home/daniel/aeon-spark-test/h3/h3-blackwell-runtime/artifacts:/artifacts:ro - /home/daniel/aeon-spark-test/h3/models/MiniMax-H3-Turbo-FL2VA/latest:/turbo:ro - /home/daniel/aeon-spark-test/h3/models/Minimax-H3-Latent-Upscaler:/latent-upscaler:ro - /home/daniel/StoryStudioAssets/H3-output:/output ports: - "8001:8000" environment: H3_DISABLE_MMAP: "1" H3_NVFP4_SCALE_BACKEND: "vortex" H3_NVFP4_SCALE_VERSION: "1" H3_SOL_QKV_LAYOUT: "native" command: ["python", "/opt/h3-blackwell-runtime/tools/serve_hot_runtime.py", "--host", "0.0.0.0", "--port", "8000", "--attention", "sage2", "--turbo-lora", "4step=/turbo/minimax_h3_fl2v_turbo_4step_v1.1_768p_comfyui_bf16.safetensors", "--turbo-lora", "8step=/turbo/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors", "--latent-upscaler", "/latent-upscaler/minimax_h3_latent_upscaler_3d_fp16.safetensors", "--warmup"]