| {"mode": "rows", "seconds": 0.005294707836583257, "physical": {"sampled_peak_physical_bytes": 32211640, "lifetime_peak_physical_bytes": 32244408, "sample_interval_s": 0.001, "sample_count": 3, "scope": "Parent process only; includes Metal; excludes compiler XPC services. Counters overlap; do not sum."}, "mlx_peak_bytes": 901120, "output_sha256": "4acd76ed7d093f0a9c07c88a77295f93d7d20199b11a9a932707e321d2afbdbf", "shape": [88, 5120], "environment": {"platform": "macOS-27.0.1-arm64-arm-64bit", "machine": "arm64", "metal": {"device_name": "Apple M5 Pro", "max_recommended_working_set_size": 55662788608, "memory_size": 68719476736, "architecture": "applegpu_g17s", "max_buffer_length": 41747087360, "resource_limit": 499000}, "versions": {"mlx": "0.32.4", "mlx-metal": "0.32.4", "numpy": "2.5.4", "safetensors": "0.8.0", "transformers": "4.57.6", "torch": "2.15.0", "Pillow": "13.0.0", "scikit-image": "0.26.0"}, "precision_environment": {"MLX_ENABLE_TF32": "0", "MLX_CONV_WINOGRAD": "0"}}, "scope": "Cold process, page-cache warm tensor read + gather only. Excludes tokenizer and full 50-layer encoder."} | |