docs(intern-decision): live on fv-ml1 GPU 1; semif marked REPLACED

intern-decision deployed 0941 PT (cap 9.0 GiB, MAX_TOKENS 7168). Live acceptance: positive control 240/259 and Wyrd 79/84, bit-identical to the bench (0/560 rows, Δp 0); negative control 10/122/14; largest accepted requests 200 with no 503; per-process 8,812 MiB at rest and 9,866 peak; GPU 1 Free 15,442 before and 6,581 after (lowest 5,569 under load). Latency from nh3-dev: 21 criteria 114 ms, 16 over ~3,900 tokens 238 ms. semif README banner now REPLACED with the rollback; fv-ml1 GPU 1 note updated.
2026-09-30 09:48:30 -07:00
parent 750675e391
commit 1cf763a7b1
10 changed files with 3957 additions and 58 deletions
@@ -0,0 +1,139 @@
+{
+ "url": "http://intern-decision.fv.internal:8033",
+ "started_utc": "2026-09-30T16:43:39Z",
+ "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": 7168,
+   "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": 7168,
+  "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": 1790786619.1466322,
+  "t_end": 1790786619.3572643
+ },
+ "maxreq": {
+  "state_chars": 4793,
+  "tokens_per_call": 7168,
+  "decisions": 64,
+  "options_each": 16,
+  "body_bytes": 96250,
+  "runs": [
+   {
+    "status": 200,
+    "e2e_ms": 1542.5,
+    "code": null,
+    "calls": 4,
+    "input_tokens": [
+     7168,
+     7168,
+     7168,
+     7168
+    ],
+    "reserved_gib_after": 7.969,
+    "max_reserved_gib": 8.996,
+    "t_end": 1790786706.9185867
+   },
+   {
+    "status": 200,
+    "e2e_ms": 1518.7,
+    "code": null,
+    "calls": 4,
+    "input_tokens": [
+     7168,
+     7168,
+     7168,
+     7168
+    ],
+    "reserved_gib_after": 7.969,
+    "max_reserved_gib": 8.996,
+    "t_end": 1790786708.4557755
+   },
+   {
+    "status": 200,
+    "e2e_ms": 1539.6,
+    "code": null,
+    "calls": 4,
+    "input_tokens": [
+     7168,
+     7168,
+     7168,
+     7168
+    ],
+    "reserved_gib_after": 7.969,
+    "max_reserved_gib": 8.996,
+    "t_end": 1790786710.014339
+   }
+  ],
+  "t_start": 1790786619.357301,
+  "t_end": 1790786710.014397
+ },
+ "maxone": {
+  "state_chars": 28727,
+  "tokens": 7168,
+  "one_more_is": [
+   422,
+   "Example has 7171 tokens, above 7168; truncation is forbidden"
+  ],
+  "runs": [
+   {
+    "status": 200,
+    "e2e_ms": 394.2,
+    "input_tokens": 7168,
+    "code": null,
+    "t_end": 1790786715.324555
+   },
+   {
+    "status": 200,
+    "e2e_ms": 375.9,
+    "input_tokens": 7168,
+    "code": null,
+    "t_end": 1790786715.7005756
+   },
+   {
+    "status": 200,
+    "e2e_ms": 372.7,
+    "input_tokens": 7168,
+    "code": null,
+    "t_end": 1790786716.0734687
+   }
+  ],
+  "pass": true,
+  "t_start": 1790786710.0144272,
+  "t_end": 1790786716.0735004
+ },
+ "finished_utc": "2026-09-30T16:45:16Z"
+}