{ "url": "http://127.0.0.1:18033", "started_utc": "2026-09-30T16:09:34Z", "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": null, "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": [] }, "auth": { "/decide": { "no_token": 401, "wrong_token": 401, "right_token": 200 }, "/decide/shared": { "no_token": 401, "wrong_token": 401, "right_token": 200 }, "health_no_token": 200, "pass": true, "t_start": 1790784574.0391982, "t_end": 1790784574.1316206 }, "chunking": { "status": [ 200, 200, 200 ], "timing": { "total_seconds": 0.14785360009409487, "batch_size": 20, "calls": 2, "questions_per_call": [ 16, 4 ], "input_tokens": [ 1884, 1328 ], "inference_seconds": 0.13485 }, "rows": [ { "id": "d0", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q1", "questions": 16 }, "sha_equal": true }, { "id": "d1", "top_whole": "no", "top_split": "no", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q2", "questions": 16 }, "sha_equal": true }, { "id": "d2", "top_whole": "no", "top_split": "no", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q3", "questions": 16 }, "sha_equal": true }, { "id": "d3", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q4", "questions": 16 }, "sha_equal": true }, { "id": "d4", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q5", "questions": 16 }, "sha_equal": true }, { "id": "d5", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q6", "questions": 16 }, "sha_equal": true }, { "id": "d6", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q7", "questions": 16 }, "sha_equal": true }, { "id": "d7", "top_whole": "no", "top_split": "no", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q8", "questions": 16 }, "sha_equal": true }, { "id": "d8", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q9", "questions": 16 }, "sha_equal": true }, { "id": "d9", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q10", "questions": 16 }, "sha_equal": true }, { "id": "d10", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q11", "questions": 16 }, "sha_equal": true }, { "id": "d11", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q12", "questions": 16 }, "sha_equal": true }, { "id": "d12", "top_whole": "no", "top_split": "no", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q13", "questions": 16 }, "sha_equal": true }, { "id": "d13", "top_whole": "no", "top_split": "no", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q14", "questions": 16 }, "sha_equal": true }, { "id": "d14", "top_whole": "no", "top_split": "no", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q15", "questions": 16 }, "sha_equal": true }, { "id": "d15", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 0, "field": "q16", "questions": 16 }, "sha_equal": true }, { "id": "d16", "top_whole": "unclear", "top_split": "unclear", "max_dp": 0.0, "call_whole": { "index": 1, "field": "q1", "questions": 4 }, "sha_equal": true }, { "id": "d17", "top_whole": "unclear", "top_split": "unclear", "max_dp": 0.0, "call_whole": { "index": 1, "field": "q2", "questions": 4 }, "sha_equal": true }, { "id": "d18", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 1, "field": "q3", "questions": 4 }, "sha_equal": true }, { "id": "d19", "top_whole": "yes", "top_split": "yes", "max_dp": 0.0, "call_whole": { "index": 1, "field": "q4", "questions": 4 }, "sha_equal": true } ], "e2e_ms": 151.3, "pass": true, "t_start": 1790784574.1316838, "t_end": 1790784574.4364655 }, "maxreq": { "state_chars": 11337, "tokens_per_call": 8192, "decisions": 64, "options_each": 16, "body_bytes": 100953, "runs": [ { "status": 422, "e2e_ms": 415.8, "code": "invalid_request", "calls": null, "input_tokens": null, "reserved_gib_after": 7.969, "max_reserved_gib": 9.557, "t_end": 1790784583.8459144 }, { "status": 422, "e2e_ms": 405.2, "code": "invalid_request", "calls": null, "input_tokens": null, "reserved_gib_after": 7.969, "max_reserved_gib": 9.557, "t_end": 1790784584.2551143 }, { "status": 422, "e2e_ms": 406.5, "code": "invalid_request", "calls": null, "input_tokens": null, "reserved_gib_after": 7.969, "max_reserved_gib": 9.557, "t_end": 1790784584.6652017 } ], "t_start": 1790784574.4365265, "t_end": 1790784584.6653428 }, "finished_utc": "2026-09-30T16:09:44Z" }