{
 "url": "http://127.0.0.1:18033",
 "started_utc": "2026-09-30T16:36:04Z",
 "health": {
  "status": "ok",
  "model": {
   "name": "Intern-Decision-4B",
   "source": "internlm/Intern-Decision-4B",
   "revision": "0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd",
   "checkpoint": "/hf/hub/models--internlm--Intern-Decision-4B/snapshots/0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd",
   "inference_py_sha256": "c904e2c67ca0775621a22375ee373d2ba30b52117cda870c6c9ef74143b29863",
   "temperature": 1.99241824,
   "dtype": "bfloat16",
   "attn_implementation": "sdpa",
   "device": "cuda",
   "max_length": 8192,
   "torch_version": "2.10.0+cu128",
   "transformers_version": "5.17.0",
   "vision_tower": "removed",
   "device_name": "NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition",
   "allocated_gib": 7.937,
   "reserved_gib": 7.969,
   "max_reserved_gib": 8.861
  },
  "vram_cap_gib": 9.0,
  "max_tokens": 8192,
  "max_decisions": 64,
  "max_questions_per_call": 16,
  "chunking": "/decide/shared questions are packed greedily, in request order, into calls of at most 16 (1-16, 17-32, ...); each call is one prompt, so the questions in a call are asked together. With orderings, ordering k of every decision forms wave k, packed the same way.",
  "workloads": []
 },
 "fit": {
  "largest_ok_state_chars": 4793,
  "largest_ok_tokens": 7168,
  "probes": [
   [
    31950,
    422,
    null
   ],
   [
    16475,
    422,
    null
   ],
   [
    8737,
    503,
    null
   ],
   [
    4868,
    503,
    null
   ],
   [
    2934,
    200,
    6772
   ],
   [
    3901,
    200,
    6964
   ],
   [
    4384,
    200,
    7056
   ],
   [
    4626,
    200,
    7133
   ],
   [
    4747,
    200,
    7156
   ],
   [
    4807,
    503,
    null
   ],
   [
    4777,
    200,
    7163
   ],
   [
    4792,
    200,
    7168
   ],
   [
    4799,
    503,
    null
   ],
   [
    4795,
    503,
    null
   ],
   [
    4793,
    200,
    7168
   ],
   [
    4794,
    503,
    null
   ]
  ],
  "t_start": 1790786164.5822356,
  "t_end": 1790786175.4811816
 },
 "maxreq": {
  "state_chars": 9508,
  "tokens_per_call": null,
  "decisions": 64,
  "options_each": 16,
  "body_bytes": 101019,
  "runs": [
   {
    "status": 503,
    "e2e_ms": 209.5,
    "code": "out_of_memory",
    "calls": null,
    "input_tokens": null,
    "reserved_gib_after": 7.969,
    "max_reserved_gib": 9.0,
    "t_end": 1790786178.99772
   }
  ],
  "t_start": 1790786175.481284,
  "t_end": 1790786178.9977298
 },
 "finished_utc": "2026-09-30T16:36:18Z"
}