{ "url": "http://10.251.50.54:8032", "health": { "status": "ok", "semif_commit": "23cf1f39fc9534fe81437200959b6dfc7106e45a", "model": { "source": "Qwen/Qwen3.5-4B", "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "dtype": "bfloat16", "device": "cuda:0", "torch_version": "2.10.0+cu128", "transformers_version": "5.17.0", "device_name": "NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition", "allocated_gib": 7.84, "reserved_gib": 8.12 }, "vram_cap_gib": 12.0, "max_tokens": 4096, "max_decisions": 64, "workloads": [] }, "1_parity_vs_upstream": { "rows": 144, "top_choice_agree": 144, "max_abs_prob_gap": 0.0595381559570336 }, "1_prompt_sha256_equal": 144, "2_noise_floor_a_vs_b": { "rows": 144, "top_choice_agree": 144, "max_abs_prob_gap": 0.0 }, "3_negative_rotated_options": { "rows": 144, "top_choice_agree": 14, "max_abs_prob_gap": 0.9987391090270772 }, "4_shared_vs_direct": { "groups": 36, "rows": 72, "top_choice_agree": 71, "max_abs_prob_gap": 0.05927145076874801 }, "5_speed_21_binary": { "prefix_tokens": 62, "shared_s": { "runs": [ 0.13865972400526516, 0.1382300010009203, 0.13749008599552326 ], "median": 0.1382300010009203 }, "sequential_decide_s": { "runs": [ 0.9489945390087087, 0.9463060130074155, 0.9458249929884914 ], "median": 0.9463060130074155 } } }