state: generation 10667 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -525,6 +525,25 @@
       "targetGpu": "Biren_166m",
       "taskType": "text-generation"
     },
+    "biren_166m|vllm|text-generation|model_type:nemotron_h": {
+      "architectureSignature": "model_type:nemotron_h",
+      "architectures": [],
+      "evidenceCount": 1,
+      "expiresAt": "2026-10-20T03:41:49.061655+00:00",
+      "framework": "vllm",
+      "latestFailureAt": "2026-09-20T03:41:49.061655+00:00",
+      "latestSuccessfulAt": null,
+      "matchType": "model_type",
+      "modelType": "nemotron_h",
+      "sourceModelIds": [
+        "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
+      ],
+      "sourceTaskIds": [
+        "4970007"
+      ],
+      "targetGpu": "Biren_166m",
+      "taskType": "text-generation"
+    },
     "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:nemotron_h": {
       "architectureSignature": "model_type:nemotron_h",
       "architectures": [],
@@ -1935,14 +1954,14 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-20T15:22:01.817445+00:00",
+  "generatedAt": "2026-09-20T15:25:29.309614+00:00",
   "summary": {
-    "activeBlockCount": 94,
+    "activeBlockCount": 95,
     "byGpuFramework": {
       "Ascend_910-b3|vllm": 11,
       "Ascend_910-b3|vllm_tokenizer_patch": 1,
       "Ascend_910-b4|vllm": 12,
-      "Biren_166m|vllm": 1,
+      "Biren_166m|vllm": 2,
       "Cambricon_mlu-370-x8|vllm": 2,
       "Cambricon_mlu-370-x8|vllm-mlu": 5,
       "Iluvatar_bi-150|transformers": 2,

.modelhub_state/market_intelligence.json

@@ -425,7 +425,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-20T15:24:27.866748+00:00",
+  "generatedAt": "2026-09-20T15:25:39.357269+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-20T15:24:27.866748+00:00",
+  "catalogUpdatedAt": "2026-09-20T15:25:39.357269+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-20T15:24:27.866748+00:00",
+  "generatedAt": "2026-09-20T15:25:39.357269+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6422,6 +6422,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-20T15:24:27.866748+00:00",
+  "taskTreeUpdatedAt": "2026-09-20T15:25:39.357269+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-20T15:22:01.735347+00:00",
+  "generatedAt": "2026-09-20T15:25:29.241097+00:00",
-  "lastSyncTime": "2026-09-20T15:22:01.055014+00:00",
+  "lastSyncTime": "2026-09-20T15:25:28.950050+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -529,6 +529,25 @@
         "targetGpu": "Biren_166m",
         "taskType": "text-generation"
       },
+      "biren_166m|vllm|text-generation|model_type:nemotron_h": {
+        "architectureSignature": "model_type:nemotron_h",
+        "architectures": [],
+        "evidenceCount": 1,
+        "expiresAt": "2026-10-20T03:41:49.061655+00:00",
+        "framework": "vllm",
+        "latestFailureAt": "2026-09-20T03:41:49.061655+00:00",
+        "latestSuccessfulAt": null,
+        "matchType": "model_type",
+        "modelType": "nemotron_h",
+        "sourceModelIds": [
+          "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
+        ],
+        "sourceTaskIds": [
+          "4970007"
+        ],
+        "targetGpu": "Biren_166m",
+        "taskType": "text-generation"
+      },
       "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:nemotron_h": {
         "architectureSignature": "model_type:nemotron_h",
         "architectures": [],
@@ -1940,12 +1959,12 @@
       }
     },
     "architectureCompatibilitySummary": {
-      "activeBlockCount": 94,
+      "activeBlockCount": 95,
       "byGpuFramework": {
         "Ascend_910-b3|vllm": 11,
         "Ascend_910-b3|vllm_tokenizer_patch": 1,
         "Ascend_910-b4|vllm": 12,
-        "Biren_166m|vllm": 1,
+        "Biren_166m|vllm": 2,
         "Cambricon_mlu-370-x8|vllm": 2,
         "Cambricon_mlu-370-x8|vllm-mlu": 5,
         "Iluvatar_bi-150|transformers": 2,
@@ -2354,27 +2373,27 @@
         "unresolvedFailureCount": 0
       },
       "Biren_166m|vllm|text-generation": {
-        "attributableFailureCount": 34,
+        "attributableFailureCount": 35,
-        "decisionFailureRate": 0.6939,
+        "decisionFailureRate": 0.7,
-        "decisionSuccessRate": 0.3061,
+        "decisionSuccessRate": 0.3,
-        "decisionTotal": 49,
+        "decisionTotal": 50,
         "failureBreakdown": {
           "ambiguous_runtime": 1,
-          "framework_architecture_unsupported": 26,
+          "framework_architecture_unsupported": 27,
           "model_load": 7,
           "tokenizer_compatibility": 1
         },
-        "failureCount": 35,
+        "failureCount": 36,
-        "failureRate": 0.7,
+        "failureRate": 0.7059,
         "framework": "vllm",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 15,
-        "successRate": 0.3,
+        "successRate": 0.2941,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 50,
+        "total": 51,
         "unresolvedFailureCount": 1
       },
       "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4452,17 +4471,17 @@
         "unresolvedFailureCount": 6405
       },
       "vllm": {
-        "attributableFailureCount": 3474,
+        "attributableFailureCount": 3475,
         "decisionFailureRate": 0.9778,
         "decisionSuccessRate": 0.0222,
-        "decisionTotal": 3553,
+        "decisionTotal": 3554,
         "failureBreakdown": {
           "ambiguous_runtime": 1434,
           "architecture_compatibility": 112,
           "attention_backend": 1,
           "backend_operator": 84,
           "context_length": 161,
-          "framework_architecture_unsupported": 1260,
+          "framework_architecture_unsupported": 1261,
           "memory_capacity": 720,
           "model_load": 198,
           "platform_infrastructure": 864,
@@ -4471,14 +4490,14 @@
           "tokenizer_compatibility": 408,
           "参数/模板问题": 40
         },
-        "failureCount": 5812,
+        "failureCount": 5813,
         "failureRate": 0.9866,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 864,
         "successCount": 79,
         "successRate": 0.0134,
-        "total": 5891,
+        "total": 5892,
         "unresolvedFailureCount": 1474
       },
       "vllm-customized": {
@@ -4612,7 +4631,7 @@
         "unresolvedFailureCount": 24
       }
     },
-    "generatedAt": "2026-09-20T15:22:01.726831+00:00",
+    "generatedAt": "2026-09-20T15:25:29.233684+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 75,
@@ -4668,15 +4687,15 @@
         "unresolvedFailureCount": 588
       },
       "Biren_166m": {
-        "attributableFailureCount": 172,
+        "attributableFailureCount": 173,
-        "decisionFailureRate": 0.8731,
+        "decisionFailureRate": 0.8737,
-        "decisionSuccessRate": 0.1269,
+        "decisionSuccessRate": 0.1263,
-        "decisionTotal": 197,
+        "decisionTotal": 198,
         "failureBreakdown": {
           "ambiguous_runtime": 131,
           "backend_operator": 4,
           "context_length": 10,
-          "framework_architecture_unsupported": 113,
+          "framework_architecture_unsupported": 114,
           "memory_capacity": 1,
           "model_load": 18,
           "platform_infrastructure": 2,
@@ -4687,14 +4706,14 @@
           "日志缺失": 62,
           "验证失败": 27
         },
-        "failureCount": 608,
+        "failureCount": 609,
-        "failureRate": 0.9605,
+        "failureRate": 0.9606,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 2,
         "successCount": 25,
-        "successRate": 0.0395,
+        "successRate": 0.0394,
-        "total": 633,
+        "total": 634,
         "unresolvedFailureCount": 434
       },
       "Cambricon_mlu-370-x4": {
@@ -5843,6 +5862,29 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Biren_166m|vllm|text-generation|nemotron_h|modelopt": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "modelType": "nemotron_h",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Biren_166m",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Biren_166m|vllm|text-generation|plamo3|none": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -11242,28 +11284,28 @@
         "unresolvedFailureCount": 5
       },
       "Biren_166m|vllm|text-generation": {
-        "attributableFailureCount": 1,
+        "attributableFailureCount": 2,
-        "consecutiveFailures": 0,
+        "consecutiveFailures": 1,
         "consecutivePlatformFailures": 0,
-        "decisionFailureRate": 0.5,
+        "decisionFailureRate": 0.6667,
-        "decisionSuccessRate": 0.5,
+        "decisionSuccessRate": 0.3333,
-        "decisionTotal": 2,
+        "decisionTotal": 3,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 1
+          "framework_architecture_unsupported": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
-        "failureRate": 0.5,
+        "failureRate": 0.6667,
         "framework": "vllm",
         "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-20T14:32:15.260751+00:00",
+        "lastTerminalAt": "2026-09-20T15:25:28.950050+00:00",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 1,
-        "successRate": 0.5,
+        "successRate": 0.3333,
         "targetGpu": "Biren_166m",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 3,
         "unresolvedFailureCount": 0
       },
       "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -11666,18 +11708,18 @@
         "unresolvedFailureCount": 0
       },
       "Sunrise_pt-200-x1|vllm|text-generation": {
-        "attributableFailureCount": 3,
+        "attributableFailureCount": 2,
-        "consecutiveFailures": 3,
+        "consecutiveFailures": 2,
         "consecutivePlatformFailures": 0,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 3,
+        "decisionTotal": 2,
         "failureBreakdown": {
           "backend_operator": 1,
-          "framework_architecture_unsupported": 2,
+          "framework_architecture_unsupported": 1,
           "platform_infrastructure": 1
         },
-        "failureCount": 4,
+        "failureCount": 3,
         "failureRate": 1.0,
         "framework": "vllm",
         "lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
@@ -11689,7 +11731,7 @@
         "successRate": 0.0,
         "targetGpu": "Sunrise_pt-200-x1",
         "taskType": "text-generation",
-        "total": 4,
+        "total": 3,
         "unresolvedFailureCount": 0
       },
       "Vastai_va16|unknown|text-generation": {
@@ -11922,6 +11964,31 @@
         "total": 3,
         "unresolvedFailureCount": 3
       },
+      "Biren_166m|vllm|text-generation|nemotron_h|modelopt": {
+        "attributableFailureCount": 1,
+        "consecutiveFailures": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "lastTerminalAt": "2026-09-20T15:25:28.950050+00:00",
+        "modelType": "nemotron_h",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Biren_166m",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Biren_166m|vllm|text-generation|qwen3|none": {
         "attributableFailureCount": 0,
         "consecutiveFailures": 0,
@@ -14342,6 +14409,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Biren_166m|vllm|text-generation|nemotron_h|modelopt|34": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "loadSizeLog2Bucket": 34,
+        "modelType": "nemotron_h",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "modelopt",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Biren_166m",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Biren_166m|vllm|text-generation|plamo3|none|33": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -22314,20 +22405,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 15876,
+    "terminalRecords": 15877,
-    "totalRecords": 15981,
+    "totalRecords": 15982,
     "totals": {
-      "attributableFailureCount": 5755,
+      "attributableFailureCount": 5756,
       "decisionFailureRate": 0.8613,
       "decisionSuccessRate": 0.1387,
-      "decisionTotal": 6682,
+      "decisionTotal": 6683,
       "failureBreakdown": {
         "ambiguous_runtime": 3770,
         "architecture_compatibility": 212,
         "attention_backend": 1,
         "backend_operator": 102,
         "context_length": 318,
-        "framework_architecture_unsupported": 1985,
+        "framework_architecture_unsupported": 1986,
         "memory_capacity": 1195,
         "model_load": 478,
         "platform_infrastructure": 922,
@@ -22338,14 +22429,14 @@
         "日志缺失": 719,
         "验证失败": 673
       },
-      "failureCount": 14949,
+      "failureCount": 14950,
       "failureRate": 0.9416,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 922,
       "successCount": 927,
       "successRate": 0.0584,
-      "total": 15876,
+      "total": 15877,
       "unresolvedFailureCount": 8272
     },
     "warnings": [
@@ -22391,12 +22482,12 @@
       "组合 Cambricon_mlu-370-x4|unknown|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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Iluvatar_bi-150|transformers|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|vllm|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。",
-      "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
+      "组合 Ascend_910-b3|vllm|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|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 15981,
+  "summarizedRecords": 15982,
   "version": 1
 }

.modelhub_state/queue_cleanup_latest.json

@@ -14,13 +14,13 @@
     100
   ],
   "accounts": 12,
-  "activeScanned": 1141,
+  "activeScanned": 1142,
   "ageCleanupMode": "admission_only",
   "agePolicySkipped": {
     "cleanupDisabled": true,
     "reason": "admission_only"
   },
-  "architectureBlockCount": 94,
+  "architectureBlockCount": 95,
   "architectureFrameworkCatalog": {
     "ascend_910-b3|text-generation": [
       "llamacpp",
@@ -37,16 +37,6 @@
       "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",
@@ -60,15 +50,6 @@
       "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"
@@ -82,10 +63,6 @@
       "sglang",
       "vllm",
       "vllm_fix_tokenizer"
-    ],
-    "vastai_va16|text-generation": [
-      "vllm",
-      "vllm_fix_tokenizer"
     ]
   },
   "architectureFrameworkCatalogErrors": {},
@@ -113,50 +90,23 @@
     "unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)",
     "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": 46,
+  "architectureModelConfigsComplete": 45,
-  "architectureOnly": false,
+  "architectureOnly": true,
   "architecturePolicySkipped": {
-    "frameworkCatalogUnknown": 0,
+    "frameworkCatalogUnknown": 3,
-    "frameworkContextUnknown": 65,
+    "frameworkContextUnknown": 62,
     "modelArchitectureUnknown": 161,
-    "noMatchingBlock": 958,
+    "noMatchingBlock": 956,
     "partiallyBlockedFrameworkSet": 22,
     "runningMatchedProtected": 0,
     "submissionContextMismatch": 0,
     "submissionContextUnknown": 0
   },
-  "cancelledCount": 1,
+  "cancelledCount": 0,
-  "cancelledTasks": [
+  "cancelledTasks": [],
-    {
+  "certainOomCount": 0,
-      "accountIndex": 4,
+  "certainOomTasks": [],
-      "cleanupReasons": [
+  "cleanupCandidateCount": 0,
-        "certain_oom_repository_size_exceeds_gpu_capacity"
-      ],
-      "gpuCapacityGiB": 100.0,
-      "gpuType": "Kunlunxin_p-800",
-      "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B",
-      "reason": "certain_oom_repository_size_exceeds_gpu_capacity",
-      "repositorySizeGiB": 132.503,
-      "requiredGiB": 159.003,
-      "status": "waiting",
-      "taskId": 4960317
-    }
-  ],
-  "certainOomCount": 1,
-  "certainOomTasks": [
-    {
-      "accountIndex": 4,
-      "gpuCapacityGiB": 100.0,
-      "gpuType": "Kunlunxin_p-800",
-      "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B",
-      "reason": "certain_oom_repository_size_exceeds_gpu_capacity",
-      "repositorySizeGiB": 132.503,
-      "requiredGiB": 159.003,
-      "status": "waiting",
-      "taskId": 4960317
-    }
-  ],
-  "cleanupCandidateCount": 1,
   "dryRun": false,
   "listingErrors": {},
   "modelAgeErrors": {},
@@ -181,20 +131,18 @@
   ],
   "oldOverflowCount": 0,
   "oldOverflowTasks": [],
-  "policyCancelledRecorded": 1,
+  "policyCancelledRecorded": 0,
   "policyNoLongerAppliesCount": 0,
   "policyNoLongerAppliesTasks": [],
   "recentModelDays": 7,
   "recentModelReserveSlots": 5,
-  "repositorySizeErrors": {
+  "repositorySizeErrors": {},
-    "empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
+  "repositorySizesComplete": 0,
-  },
-  "repositorySizesComplete": 339,
   "skipped": {
-    "fitsKnownCapacity": 1138,
+    "fitsKnownCapacity": 0,
     "gpuCapacityUnknown": 0,
-    "repositorySizeUnknown": 2
+    "repositorySizeUnknown": 0
   },
   "stopErrors": [],
-  "uniqueModels": 340
+  "uniqueModels": 348
 }

.modelhub_state/recent_outcomes.jsonl

@@ -65,6 +65,7 @@
 {"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": "2026-09-20T12:01:00.671326+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.297736+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970018", "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": "2026-09-20T12:01:00.671111+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "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:m1", "custom_tag:m2", "custom_tag:fp16", "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:coding", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.292011+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970019", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671190+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.160353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970010", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-20T15:25:28.950050+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:41:49.061655+00:00", "targetGpu": "Biren_166m", "taskId": "4970007", "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": ["zaya"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.670566+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": "2026-09-20T03:41:48.973538+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969997", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.671259+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "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": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:48.972177+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969999", "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": "2026-09-20T11:37:54.215258+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "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": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:32.546681+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969665", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-14T03:38:15.505403+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T03:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596909", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:51:59.045472+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4493314", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:14:40.319417+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4582655", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-14T00:51:56.404636+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T00:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490280", "taskType": "text-generation", "verifyResult": -1}

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.20.2",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "0decf826c0024381e3df5e7f1189d6018da9db06481a945e98b9103d435d85b3",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "3bafcaaa4183eb78ad6de463f3d22e738174a004d4a8e0721c92282d35a94d8b",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "9e09d9ed7e824b21c27d9b3bc28ce8edf8d4e1899b405477de3b6c2c7dfedc25",
+    ".modelhub_state/market_intelligence.json": "2a949827bdc04a893252b538ba21fc668066e9c38325fb6cf7b01104f0cd6d11",
-    ".modelhub_state/official_capabilities.json": "e1acf942d1bd77d8fa97c5c7dd7df8afa8ee94f7e6f679ffe157901af15a0435",
+    ".modelhub_state/official_capabilities.json": "1e1332c36866679347ffb8a39febdb47e234ed666fe2d8bbbbe670b920246079",
-    ".modelhub_state/outcome_checkpoint.json": "33167721bd89d7a994e77250323bef69e08b47f0dcdd5ef651fb20470c1228b6",
+    ".modelhub_state/outcome_checkpoint.json": "10e3918da172437e6af2f0ae6e1f2205c22d3e34e2fa5057df98ba5cd0dcadcc",
-    ".modelhub_state/queue_cleanup_latest.json": "eb01f106d0cd4018a0346c4a81182d6a9e67f5d4d14db22f5d0c685667977bc3",
+    ".modelhub_state/queue_cleanup_latest.json": "c08f8d05133b1c670eeecc05c2f1f58fb85c2589e80bc520cfd00c86c079ea31",
-    ".modelhub_state/recent_outcomes.jsonl": "797b673379b78d4e9c0a3368346587ded2ab96ef3077c1cadbcf995d05066a03",
+    ".modelhub_state/recent_outcomes.jsonl": "d1466ee838fc190fdb7539086ac94546eeb50f228df6ba94f4145cbc532d2f63",
-    ".modelhub_state/recovery_active_tasks.jsonl": "3b2b0ff7f207790c0bbbc7467ba2b980753b5856f44412ca19eecc782247faad",
+    ".modelhub_state/recovery_active_tasks.jsonl": "b2baaa5c5b3c924f82938d5e2957da734417380466373aa35708bf6c3c1fd10e",
-    ".modelhub_state/recovery_intents.jsonl": "e31a6d7cdbb3d07b3e1495bae8fbbd2d4dc2f60e9c85fd3d50f80157f42d2fd4",
+    ".modelhub_state/recovery_intents.jsonl": "5b415e0884eb55105786a714f8d2f763a1e597f8feabe34163c3684c25f83b26",
     ".modelhub_state/routing_intelligence.json": "a88462c005b631d7d444c0c5e9f25343d7005c88c0d2eed54f74958e8f567859",
     ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
     ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
     "ledger/submissions.jsonl": "f4362ab94c40479a82932013c5e2de1d237326ea2df827a2e131475e45089c2d",
-    "outcomes/submissions.jsonl": "602840c774a941919864acb3bda477024fe5df2b052b4305a4064a8b5ab4fcf5"
+    "outcomes/submissions.jsonl": "b98e6fbbf66047ac8a58810053263a7e60d38403376d560486a6940c70516a99"
   },
-  "generation": 10666,
+  "generation": 10667,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-20T15:24:28.311753+00:00",
+  "updatedAt": "2026-09-20T15:25:40.243954+00:00",
   "writerId": "fc715c06e24c4db2ae3e425e435db996"
 }

outcomes/submissions.jsonl

@@ -783,7 +783,6 @@
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:48.969580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969996", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670508+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.003635+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970004", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.670934+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:48.995904+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970001", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.061655+00:00", "targetGpu": "Biren_166m", "taskId": "4970007", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671009+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.141735+00:00", "targetGpu": "Biren_166m", "taskId": "4970017", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.155389+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970012", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "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": 8239718268}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:41:49.135089+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970008", "taskType": "text-generation", "verifyResult": null}