state: generation 11839 (cycle_no_slots)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1626,6 +1626,27 @@
       "targetGpu": "Iluvatar_bi-150",
       "taskType": "text-generation"
     },
+    "iluvatar_bi-150|transformers|text-generation|architectures:zayaforcausallm": {
+      "architectureSignature": "architectures:zayaforcausallm",
+      "architectures": [
+        "zayaforcausallm"
+      ],
+      "evidenceCount": 1,
+      "expiresAt": "2026-10-21T14:20:21.627234+00:00",
+      "framework": "transformers",
+      "latestFailureAt": "2026-09-21T14:20:21.627234+00:00",
+      "latestSuccessfulAt": null,
+      "matchType": "architectures",
+      "modelType": "zaya",
+      "sourceModelIds": [
+        "JANGQ-AI/AppleScript-8B-JANG_4M"
+      ],
+      "sourceTaskIds": [
+        "5002168"
+      ],
+      "targetGpu": "Iluvatar_bi-150",
+      "taskType": "text-generation"
+    },
     "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:gemma4": {
       "architectureSignature": "model_type:gemma4",
       "architectures": [],
@@ -2848,9 +2869,9 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-21T22:32:08.558272+00:00",
+  "generatedAt": "2026-09-21T22:33:35.735992+00:00",
   "summary": {
-    "activeBlockCount": 143,
+    "activeBlockCount": 144,
     "byGpuFramework": {
       "Ascend_910-b3|vllm": 13,
       "Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2861,7 +2882,7 @@
       "Cambricon_mlu-370-x8|vllm": 16,
       "Cambricon_mlu-370-x8|vllm-customized": 2,
       "Cambricon_mlu-370-x8|vllm-mlu": 5,
-      "Iluvatar_bi-150|transformers": 4,
+      "Iluvatar_bi-150|transformers": 5,
       "Iluvatar_bi-150|vllm": 8,
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
       "Iluvatar_bi-150|vllm_tokenizer_patch": 2,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-21T22:25:09.094897+00:00",
+  "generatedAt": "2026-09-21T22:33:35.651361+00:00",
-  "lastSyncTime": "2026-09-21T22:25:08.760152+00:00",
+  "lastSyncTime": "2026-09-21T22:33:35.352115+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -1630,6 +1630,27 @@
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation"
       },
+      "iluvatar_bi-150|transformers|text-generation|architectures:zayaforcausallm": {
+        "architectureSignature": "architectures:zayaforcausallm",
+        "architectures": [
+          "zayaforcausallm"
+        ],
+        "evidenceCount": 1,
+        "expiresAt": "2026-10-21T14:20:21.627234+00:00",
+        "framework": "transformers",
+        "latestFailureAt": "2026-09-21T14:20:21.627234+00:00",
+        "latestSuccessfulAt": null,
+        "matchType": "architectures",
+        "modelType": "zaya",
+        "sourceModelIds": [
+          "JANGQ-AI/AppleScript-8B-JANG_4M"
+        ],
+        "sourceTaskIds": [
+          "5002168"
+        ],
+        "targetGpu": "Iluvatar_bi-150",
+        "taskType": "text-generation"
+      },
       "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:gemma4": {
         "architectureSignature": "model_type:gemma4",
         "architectures": [],
@@ -2853,7 +2874,7 @@
       }
     },
     "architectureCompatibilitySummary": {
-      "activeBlockCount": 143,
+      "activeBlockCount": 144,
       "byGpuFramework": {
         "Ascend_910-b3|vllm": 13,
         "Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2864,7 +2885,7 @@
         "Cambricon_mlu-370-x8|vllm": 16,
         "Cambricon_mlu-370-x8|vllm-customized": 2,
         "Cambricon_mlu-370-x8|vllm-mlu": 5,
-        "Iluvatar_bi-150|transformers": 4,
+        "Iluvatar_bi-150|transformers": 5,
         "Iluvatar_bi-150|vllm": 8,
         "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
         "Iluvatar_bi-150|vllm_tokenizer_patch": 2,
@@ -3859,18 +3880,18 @@
         "unresolvedFailureCount": 0
       },
       "Iluvatar_bi-150|transformers|text-generation": {
-        "attributableFailureCount": 25,
+        "attributableFailureCount": 26,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 25,
+        "decisionTotal": 26,
         "failureBreakdown": {
           "ambiguous_runtime": 9,
-          "framework_architecture_unsupported": 6,
+          "framework_architecture_unsupported": 7,
           "memory_capacity": 5,
           "model_load": 2,
           "tokenizer_compatibility": 12
         },
-        "failureCount": 34,
+        "failureCount": 35,
         "failureRate": 1.0,
         "framework": "transformers",
         "pendingCount": 0,
@@ -3880,7 +3901,7 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 34,
+        "total": 35,
         "unresolvedFailureCount": 9
       },
       "Iluvatar_bi-150|unknown|asr": {
@@ -4120,10 +4141,10 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 7,
         "failureBreakdown": {
-          "ambiguous_runtime": 33,
+          "ambiguous_runtime": 35,
           "memory_capacity": 7
         },
-        "failureCount": 40,
+        "failureCount": 42,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
@@ -4133,8 +4154,8 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 40,
+        "total": 42,
-        "unresolvedFailureCount": 33
+        "unresolvedFailureCount": 35
       },
       "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
         "attributableFailureCount": 6,
@@ -5451,25 +5472,25 @@
         "unresolvedFailureCount": 116
       },
       "transformers": {
-        "attributableFailureCount": 26,
+        "attributableFailureCount": 27,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 26,
+        "decisionTotal": 27,
         "failureBreakdown": {
           "ambiguous_runtime": 61,
-          "framework_architecture_unsupported": 7,
+          "framework_architecture_unsupported": 8,
           "memory_capacity": 5,
           "model_load": 2,
           "tokenizer_compatibility": 12
         },
-        "failureCount": 87,
+        "failureCount": 88,
         "failureRate": 1.0,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 0,
         "successRate": 0.0,
-        "total": 87,
+        "total": 88,
         "unresolvedFailureCount": 61
       },
       "unknown": {
@@ -5630,7 +5651,7 @@
         "decisionSuccessRate": 0.0391,
         "decisionTotal": 128,
         "failureBreakdown": {
-          "ambiguous_runtime": 207,
+          "ambiguous_runtime": 209,
           "backend_operator": 8,
           "framework_architecture_unsupported": 23,
           "memory_capacity": 7,
@@ -5639,15 +5660,15 @@
           "tokenizer_compatibility": 82,
           "参数/模板问题": 13
         },
-        "failureCount": 360,
+        "failureCount": 362,
-        "failureRate": 0.9863,
+        "failureRate": 0.9864,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 17,
         "successCount": 5,
-        "successRate": 0.0137,
+        "successRate": 0.0136,
-        "total": 365,
+        "total": 367,
-        "unresolvedFailureCount": 220
+        "unresolvedFailureCount": 222
       },
       "vllm_tokenizer_patch": {
         "attributableFailureCount": 78,
@@ -5677,7 +5698,7 @@
         "unresolvedFailureCount": 120
       }
     },
-    "generatedAt": "2026-09-21T22:25:09.082653+00:00",
+    "generatedAt": "2026-09-21T22:33:35.637691+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 99,
@@ -5840,16 +5861,16 @@
         "unresolvedFailureCount": 568
       },
       "Iluvatar_bi-150": {
-        "attributableFailureCount": 749,
+        "attributableFailureCount": 750,
-        "decisionFailureRate": 0.8341,
+        "decisionFailureRate": 0.8343,
-        "decisionSuccessRate": 0.1659,
+        "decisionSuccessRate": 0.1657,
-        "decisionTotal": 898,
+        "decisionTotal": 899,
         "failureBreakdown": {
-          "ambiguous_runtime": 623,
+          "ambiguous_runtime": 625,
           "architecture_compatibility": 15,
           "backend_operator": 12,
           "context_length": 29,
-          "framework_architecture_unsupported": 247,
+          "framework_architecture_unsupported": 248,
           "memory_capacity": 151,
           "model_load": 125,
           "platform_infrastructure": 21,
@@ -5860,15 +5881,15 @@
           "日志缺失": 155,
           "验证失败": 30
         },
-        "failureCount": 1898,
+        "failureCount": 1901,
-        "failureRate": 0.9272,
+        "failureRate": 0.9273,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 21,
         "successCount": 149,
-        "successRate": 0.0728,
+        "successRate": 0.0727,
-        "total": 2047,
+        "total": 2050,
-        "unresolvedFailureCount": 1128
+        "unresolvedFailureCount": 1130
       },
       "Iluvatar_mrv-100": {
         "attributableFailureCount": 968,
@@ -11933,6 +11954,29 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Iluvatar_bi-150|transformers|text-generation|zaya|none": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "transformers",
+        "modelType": "zaya",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_bi-150",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bailing_hybrid|none": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -12745,9 +12789,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "modelType": "gemma2",
@@ -12759,8 +12803,8 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
         "attributableFailureCount": 0,
@@ -13206,9 +13250,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "modelType": "starcoder2",
@@ -13220,8 +13264,8 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|gemma4|none": {
         "attributableFailureCount": 2,
@@ -18041,15 +18085,15 @@
         "unresolvedFailureCount": 17
       },
       "Iluvatar_bi-150|transformers|text-generation": {
-        "attributableFailureCount": 14,
+        "attributableFailureCount": 15,
-        "consecutiveFailures": 14,
+        "consecutiveFailures": 15,
         "consecutivePlatformFailures": 0,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 14,
+        "decisionTotal": 15,
         "failureBreakdown": {
-          "ambiguous_runtime": 6,
+          "ambiguous_runtime": 5,
-          "framework_architecture_unsupported": 5,
+          "framework_architecture_unsupported": 6,
           "memory_capacity": 1,
           "tokenizer_compatibility": 8
         },
@@ -18057,7 +18101,7 @@
         "failureRate": 1.0,
         "framework": "transformers",
         "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-21T20:22:53.859269+00:00",
+        "lastTerminalAt": "2026-09-21T22:33:35.352083+00:00",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
@@ -18066,7 +18110,7 @@
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
         "total": 20,
-        "unresolvedFailureCount": 6
+        "unresolvedFailureCount": 5
       },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
         "attributableFailureCount": 4,
@@ -18113,7 +18157,7 @@
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-21T20:22:53.859210+00:00",
+        "lastTerminalAt": "2026-09-21T22:33:35.352105+00:00",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
@@ -20592,6 +20636,31 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Iluvatar_bi-150|transformers|text-generation|zaya|none": {
+        "attributableFailureCount": 1,
+        "consecutiveFailures": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "transformers",
+        "lastTerminalAt": "2026-09-21T22:33:35.352083+00:00",
+        "modelType": "zaya",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_bi-150",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bailing_hybrid|none": {
         "attributableFailureCount": 1,
         "consecutiveFailures": 1,
@@ -20850,12 +20919,12 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-20T17:24:32.660437+00:00",
+        "lastTerminalAt": "2026-09-21T22:33:35.352115+00:00",
         "modelType": "gemma2",
         "pendingCount": 0,
         "pendingRate": 0.0,
@@ -20865,8 +20934,8 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none": {
         "attributableFailureCount": 0,
@@ -21094,81 +21163,6 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
-      "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
-        "attributableFailureCount": 1,
-        "consecutiveFailures": 1,
-        "decisionFailureRate": 1.0,
-        "decisionSuccessRate": 0.0,
-        "decisionTotal": 1,
-        "failureBreakdown": {
-          "memory_capacity": 1
-        },
-        "failureCount": 1,
-        "failureRate": 1.0,
-        "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-20T12:21:49.901832+00:00",
-        "modelType": "qwen3_5",
-        "pendingCount": 0,
-        "pendingRate": 0.0,
-        "platformFailureCount": 0,
-        "quantizationMethod": "none",
-        "successCount": 0,
-        "successRate": 0.0,
-        "targetGpu": "Iluvatar_bi-150",
-        "taskType": "text-generation",
-        "total": 1,
-        "unresolvedFailureCount": 0
-      },
-      "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
-        "attributableFailureCount": 0,
-        "consecutiveFailures": 0,
-        "decisionFailureRate": 0.0,
-        "decisionSuccessRate": 0.0,
-        "decisionTotal": 0,
-        "failureBreakdown": {
-          "ambiguous_runtime": 1
-        },
-        "failureCount": 1,
-        "failureRate": 1.0,
-        "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-20T12:21:49.901942+00:00",
-        "modelType": "spark2_5",
-        "pendingCount": 0,
-        "pendingRate": 0.0,
-        "platformFailureCount": 0,
-        "quantizationMethod": "fp8",
-        "successCount": 0,
-        "successRate": 0.0,
-        "targetGpu": "Iluvatar_bi-150",
-        "taskType": "text-generation",
-        "total": 1,
-        "unresolvedFailureCount": 1
-      },
-      "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|none": {
-        "attributableFailureCount": 0,
-        "consecutiveFailures": 0,
-        "decisionFailureRate": 0.0,
-        "decisionSuccessRate": 0.0,
-        "decisionTotal": 0,
-        "failureBreakdown": {
-          "ambiguous_runtime": 1
-        },
-        "failureCount": 1,
-        "failureRate": 1.0,
-        "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-20T12:21:49.901876+00:00",
-        "modelType": "spark2_5",
-        "pendingCount": 0,
-        "pendingRate": 0.0,
-        "platformFailureCount": 0,
-        "quantizationMethod": "none",
-        "successCount": 0,
-        "successRate": 0.0,
-        "targetGpu": "Iluvatar_bi-150",
-        "taskType": "text-generation",
-        "total": 1,
-        "unresolvedFailureCount": 1
-      },
       "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
         "attributableFailureCount": 0,
         "consecutiveFailures": 0,
@@ -21176,12 +21170,12 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
-        "lastTerminalAt": "2026-09-20T17:24:32.660469+00:00",
+        "lastTerminalAt": "2026-09-21T22:33:35.352105+00:00",
         "modelType": "starcoder2",
         "pendingCount": 0,
         "pendingRate": 0.0,
@@ -21191,8 +21185,8 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|gemma4|none": {
         "attributableFailureCount": 2,
@@ -29925,6 +29919,30 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Iluvatar_bi-150|transformers|text-generation|zaya|none|32": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "transformers",
+        "loadSizeLog2Bucket": 32,
+        "modelType": "zaya",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_bi-150",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bailing_hybrid|none|33": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -31168,9 +31186,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm_fix_tokenizer",
         "loadSizeLog2Bucket": 32,
@@ -31183,8 +31201,8 @@
         "successRate": 0.0,
         "targetGpu": "Iluvatar_bi-150",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": {
         "attributableFailureCount": 0,
@@ -31835,6 +31853,30 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|33": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 33,
+        "modelType": "starcoder2",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "compressed-tensors",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Iluvatar_bi-150",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|gemma4|none|32": {
         "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
@@ -38463,20 +38505,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 16429,
+    "terminalRecords": 16432,
-    "totalRecords": 16623,
+    "totalRecords": 16626,
     "totals": {
-      "attributableFailureCount": 5921,
+      "attributableFailureCount": 5922,
       "decisionFailureRate": 0.8619,
       "decisionSuccessRate": 0.1381,
-      "decisionTotal": 6870,
+      "decisionTotal": 6871,
       "failureBreakdown": {
-        "ambiguous_runtime": 4049,
+        "ambiguous_runtime": 4051,
         "architecture_compatibility": 212,
         "attention_backend": 1,
         "backend_operator": 105,
         "context_length": 321,
-        "framework_architecture_unsupported": 2093,
+        "framework_architecture_unsupported": 2094,
         "memory_capacity": 1199,
         "model_load": 500,
         "platform_infrastructure": 925,
@@ -38487,31 +38529,31 @@
         "日志缺失": 719,
         "验证失败": 674
       },
-      "failureCount": 15480,
+      "failureCount": 15483,
       "failureRate": 0.9422,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 925,
       "successCount": 949,
       "successRate": 0.0578,
-      "total": 16429,
+      "total": 16432,
-      "unresolvedFailureCount": 8634
+      "unresolvedFailureCount": 8636
     },
     "warnings": [
       "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -38551,6 +38593,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 16623,
+  "summarizedRecords": 16626,
   "version": 1
 }

.modelhub_state/queue_cleanup_latest.json

@@ -20,7 +20,7 @@
     "cleanupDisabled": true,
     "reason": "admission_only"
   },
-  "architectureBlockCount": 143,
+  "architectureBlockCount": 144,
   "architectureFrameworkCatalog": {
     "ascend_910-b3|text-generation": [
       "llamacpp",
@@ -38,27 +38,11 @@
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
-    "cambricon_mlu-370-x4|text-generation": [
-      "vllm",
-      "vllm-customized",
-      "vllm-mlu"
-    ],
-    "cambricon_mlu-370-x8|text-generation": [
-      "vllm",
-      "vllm-customized",
-      "vllm-mlu"
-    ],
     "hygon_k100-ai|text-generation": [
       "llamacpp",
       "vllm",
       "vllm-patch-tokenizer"
     ],
-    "iluvatar_bi-100|text-generation": [
-      "transformers",
-      "vllm",
-      "vllm-patch-tokenizer",
-      "vllm_fix_tokenizer"
-    ],
     "iluvatar_bi-150|text-generation": [
       "llamacpp",
       "transformers",
@@ -67,19 +51,11 @@
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
-    "iluvatar_mrv-100|text-generation": [
-      "transformers",
-      "vllm"
-    ],
     "kunlunxin_p-800|text-generation": [
       "vllm",
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
-    "metax_c-500|text-generation": [
-      "vllm",
-      "vllm_tokenizer_patch"
-    ],
     "mthreads_s4000|text-generation": [
       "llamacpp",
       "vllm",
@@ -89,10 +65,6 @@
       "sglang",
       "vllm",
       "vllm_fix_tokenizer"
-    ],
-    "vastai_va16|text-generation": [
-      "vllm",
-      "vllm_fix_tokenizer"
     ]
   },
   "architectureFrameworkCatalogErrors": {},
@@ -121,7 +93,7 @@
     "z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
   },
   "architectureModelConfigsComplete": 56,
-  "architectureOnly": false,
+  "architectureOnly": true,
   "architecturePolicySkipped": {
     "frameworkCatalogUnknown": 0,
     "frameworkContextUnknown": 62,
@@ -166,14 +138,12 @@
   "policyNoLongerAppliesTasks": [],
   "recentModelDays": 7,
   "recentModelReserveSlots": 5,
-  "repositorySizeErrors": {
+  "repositorySizeErrors": {},
-    "empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
+  "repositorySizesComplete": 0,
-  },
-  "repositorySizesComplete": 381,
   "skipped": {
-    "fitsKnownCapacity": 1198,
+    "fitsKnownCapacity": 0,
     "gpuCapacityUnknown": 0,
-    "repositorySizeUnknown": 2
+    "repositorySizeUnknown": 0
   },
   "stopErrors": [],
   "uniqueModels": 382

.modelhub_state/recent_outcomes.jsonl

@@ -4,6 +4,9 @@
 {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-21T15:14:12.874625+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T15:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610383", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876304+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:47:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4586965", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-21T14:32:55.759858+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4584252", "taskType": "text-generation", "verifyResult": -1}
+{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-21T22:33:35.352083+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:20:21.627234+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002168", "taskType": "text-generation", "verifyResult": -1}
+{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:33:35.352105+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T17:24:32.660469+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16568142341}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:17:59.395147+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002153", "taskType": "text-generation", "verifyResult": -1}
+{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:33:35.352115+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T17:24:32.660437+00:00", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 7985124714}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:17:59.387901+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002151", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T20:22:53.859282+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.453427+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000553", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T20:22:53.859263+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.451262+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000554", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-21T20:22:53.859269+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"tokenizer_compatibility": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-20T13:30:42.155893+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:10:32.448125+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5000552", "taskType": "text-generation", "verifyResult": -1}
@@ -295,6 +298,3 @@
 {"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901701+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902137+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.340891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970366", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T12:21:49.902066+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.338170+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970365", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901832+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.335892+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970367", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901876+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.302188+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970362", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901942+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.300812+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970363", "taskType": "text-generation", "verifyResult": -1}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.20.2",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "877ed88e1e8214872cee74d86d7fde994a7203bd12e87bdba5b20b9aabdab945",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "d596196aa21e73f5c2d026246000c7caedee793b85133bc9fcdf923442520209",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
     ".modelhub_state/market_intelligence.json": "1ab2355d2556a6531557e252eeef4cf4f5bef90491dc0566e57c796c93e86557",
     ".modelhub_state/official_capabilities.json": "4af4f484276982874ed30d17647143d7e1bd27f5315d79545e6f0de016c8e17a",
-    ".modelhub_state/outcome_checkpoint.json": "1ac3834ff627ead1a46090077468677e2923422fb715dc2e8b9b16d742417b8c",
+    ".modelhub_state/outcome_checkpoint.json": "8493890507d3ee23b25ed8f5e766c4aff682c477bfcd26aaf61462d179c5766d",
-    ".modelhub_state/queue_cleanup_latest.json": "684035bc75f3dccb9a852d9244b8cb34bfbaacc084ca3256703fc8b0e9da3555",
+    ".modelhub_state/queue_cleanup_latest.json": "b1b7282c6b358c385382f40f1d98c1271162d249ef523e283e95261951a8cd2b",
-    ".modelhub_state/recent_outcomes.jsonl": "d76938e9d26a2a0d236e803b78831acf8b9dc0145baeb776d0e75f012f5387ee",
+    ".modelhub_state/recent_outcomes.jsonl": "baeb589eaf964b4bdb0cba3e24511b77170b513d2e846b566e3a6736c45deede",
-    ".modelhub_state/recovery_active_tasks.jsonl": "b4058b845416c5492f2b1aed8a96c44538d5e71b89e8ab4e0ef9580ae8087cd2",
+    ".modelhub_state/recovery_active_tasks.jsonl": "d66986726c728a196be7c968d89f7043ea1c94e283f941f965bce5e79785ba86",
-    ".modelhub_state/recovery_intents.jsonl": "a1c66a8981bc5872b3600b3f38fd2e490520b5efe796c943e2357b129c38a3df",
+    ".modelhub_state/recovery_intents.jsonl": "c7e48abaa9672d0625753ba623b4d7dc825b8a02ed7d09f95b5fac4b3b040de2",
     ".modelhub_state/routing_intelligence.json": "2e1a52628be3aaf9ce60bf00f6b3864251d98c725aad3b03e7686b3d6c546ca6",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
     "ledger/submissions.jsonl": "e412022ddaf557622e2bc2fbaea013d00f061076e15395fc6200e97b06991728",
-    "outcomes/submissions.jsonl": "1d32d8c4e4889429942b61d26d3a41d774244ad7c1e8ee5b3b4bbe95a0faf75f"
+    "outcomes/submissions.jsonl": "a6ee39903b1e0e4d72c83554909197b2d9ac5e42f22a767c5b647186dbb9e92c"
   },
-  "generation": 11838,
+  "generation": 11839,
   "phase": "cycle_no_slots",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-21T22:32:24.601657+00:00",
+  "updatedAt": "2026-09-21T22:33:52.182207+00:00",
   "writerId": "8b35139af6674067a339a670222d4b67"
 }

outcomes/submissions.jsonl

@@ -1001,10 +1001,7 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:18:38.160867+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36679335352, "estimatedRequiredGiB": 41.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 36711610638, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18339618304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:pruning", "custom_tag:width-pruning", "custom_tag:zero-training", "custom_tag:qwen3_5", "custom_tag:gated-deltanet"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T12:09:51.363816+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 36711610638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:17:59.392335+00:00", "targetGpu": "Biren_166m", "taskId": "5002152", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:18:38.160890+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T12:09:51.363816+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:17:59.385934+00:00", "targetGpu": "Biren_166m", "taskId": "5002154", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:17:59.369215+00:00", "targetGpu": "Biren_166m", "taskId": "5002150", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T17:24:32.660469+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16568142341}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:17:59.395147+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002153", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T17:24:32.660437+00:00", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:17:59.387901+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002151", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:22:17.565308+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:18:50.561697+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002167", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:20:21.627234+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002168", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T22:23:42.064201+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:20:50.936887+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5002188", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"tokenizer_compatibility": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T21:06:45.850258+00:00", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:22:53.836064+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002202", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175161, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018175161}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T14:48:11.808469+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5002501", "taskType": "text-generation", "verifyResult": null}