{ "status": "passed", "scope": "one synthetic RGB image; inference smoke only; not an accuracy benchmark", "inference_file_sha256": "caae30c86c404c1329534dad4cd67bcbaa65040b03c49f86cbc4b8a877be8381", "versions": { "python": "3.11.0", "torch": "2.5.1+cu121", "transformers": "4.57.0.dev0", "accelerate": "1.13.0", "cuda_runtime": "12.1" }, "model_dtype": "torch.bfloat16", "input_tokens": 68, "generated_tokens": 2, "image_grid_thw": [ [ 1, 14, 14 ] ], "answer": "Red", "checks": { "config_loaded": true, "tokenizer_loaded": true, "processor_loaded": true, "short_image_generation": true }, "note": "SDPA, deterministic decoding; synthetic test; not an accuracy or speed benchmark." }