state: generation 10879 (intent)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -22,22 +22,43 @@
     "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
       "architectureSignature": "model_type:qwen3_5",
       "architectures": [],
-      "evidenceCount": 1,
+      "evidenceCount": 2,
-      "expiresAt": "2026-10-20T02:52:51.682339+00:00",
+      "expiresAt": "2026-10-20T02:52:51.741993+00:00",
       "framework": "vllm_tokenizer_patch",
-      "latestFailureAt": "2026-09-20T02:52:51.682339+00:00",
+      "latestFailureAt": "2026-09-20T02:52:51.741993+00:00",
       "latestSuccessfulAt": null,
       "matchType": "model_type",
       "modelType": "qwen3_5",
       "sourceModelIds": [
+        "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16",
         "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo"
       ],
       "sourceTaskIds": [
+        "4969059",
         "4969056"
       ],
       "targetGpu": "Ascend_910-b3",
       "taskType": "text-generation"
     },
+    "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectures": [],
+      "evidenceCount": 1,
+      "expiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "framework": "vllm_tokenizer_patch",
+      "latestFailureAt": "2026-09-20T02:52:51.748956+00:00",
+      "latestSuccessfulAt": null,
+      "matchType": "model_type",
+      "modelType": "qwen3_5_moe",
+      "sourceModelIds": [
+        "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B"
+      ],
+      "sourceTaskIds": [
+        "4969058"
+      ],
+      "targetGpu": "Ascend_910-b3",
+      "taskType": "text-generation"
+    },
     "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_vl": {
       "architectureSignature": "model_type:qwen3_vl",
       "architectures": [],
@@ -2165,12 +2186,12 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-20T20:13:02.030852+00:00",
+  "generatedAt": "2026-09-20T20:16:31.335741+00:00",
   "summary": {
-    "activeBlockCount": 106,
+    "activeBlockCount": 107,
     "byGpuFramework": {
       "Ascend_910-b3|vllm": 11,
-      "Ascend_910-b3|vllm_tokenizer_patch": 3,
+      "Ascend_910-b3|vllm_tokenizer_patch": 4,
       "Ascend_910-b4|vllm": 12,
       "Biren_166m|vllm": 3,
       "Cambricon_mlu-370-x8|vllm": 6,

.modelhub_state/market_intelligence.json

@@ -425,7 +425,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-20T20:15:28.669777+00:00",
+  "generatedAt": "2026-09-20T20:16:41.563024+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-20T20:15:28.669777+00:00",
+  "catalogUpdatedAt": "2026-09-20T20:16:41.563024+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-20T20:15:28.669777+00:00",
+  "generatedAt": "2026-09-20T20:16:41.563024+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6380,6 +6380,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-20T20:15:28.669777+00:00",
+  "taskTreeUpdatedAt": "2026-09-20T20:16:41.563024+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-20T20:09:42.288885+00:00",
+  "generatedAt": "2026-09-20T20:16:41.504174+00:00",
-  "lastSyncTime": "2026-09-20T20:09:42.231470+00:00",
+  "lastSyncTime": "2026-09-20T20:16:41.418076+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -26,22 +26,43 @@
       "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
         "architectureSignature": "model_type:qwen3_5",
         "architectures": [],
-        "evidenceCount": 1,
+        "evidenceCount": 2,
-        "expiresAt": "2026-10-20T02:52:51.682339+00:00",
+        "expiresAt": "2026-10-20T02:52:51.741993+00:00",
         "framework": "vllm_tokenizer_patch",
-        "latestFailureAt": "2026-09-20T02:52:51.682339+00:00",
+        "latestFailureAt": "2026-09-20T02:52:51.741993+00:00",
         "latestSuccessfulAt": null,
         "matchType": "model_type",
         "modelType": "qwen3_5",
         "sourceModelIds": [
+          "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16",
           "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo"
         ],
         "sourceTaskIds": [
+          "4969059",
           "4969056"
         ],
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation"
       },
+      "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
+        "architectureSignature": "model_type:qwen3_5_moe",
+        "architectures": [],
+        "evidenceCount": 1,
+        "expiresAt": "2026-10-20T02:52:51.748956+00:00",
+        "framework": "vllm_tokenizer_patch",
+        "latestFailureAt": "2026-09-20T02:52:51.748956+00:00",
+        "latestSuccessfulAt": null,
+        "matchType": "model_type",
+        "modelType": "qwen3_5_moe",
+        "sourceModelIds": [
+          "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B"
+        ],
+        "sourceTaskIds": [
+          "4969058"
+        ],
+        "targetGpu": "Ascend_910-b3",
+        "taskType": "text-generation"
+      },
       "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_vl": {
         "architectureSignature": "model_type:qwen3_vl",
         "architectures": [],
@@ -2170,10 +2191,10 @@
       }
     },
     "architectureCompatibilitySummary": {
-      "activeBlockCount": 106,
+      "activeBlockCount": 107,
       "byGpuFramework": {
         "Ascend_910-b3|vllm": 11,
-        "Ascend_910-b3|vllm_tokenizer_patch": 3,
+        "Ascend_910-b3|vllm_tokenizer_patch": 4,
         "Ascend_910-b4|vllm": 12,
         "Biren_166m|vllm": 3,
         "Cambricon_mlu-370-x8|vllm": 6,
@@ -2282,25 +2303,25 @@
         "unresolvedFailureCount": 1
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
-        "attributableFailureCount": 17,
+        "attributableFailureCount": 19,
-        "decisionFailureRate": 0.8947,
+        "decisionFailureRate": 0.9048,
-        "decisionSuccessRate": 0.1053,
+        "decisionSuccessRate": 0.0952,
-        "decisionTotal": 19,
+        "decisionTotal": 21,
         "failureBreakdown": {
           "ambiguous_runtime": 12,
-          "framework_architecture_unsupported": 17
+          "framework_architecture_unsupported": 19
         },
-        "failureCount": 29,
+        "failureCount": 31,
-        "failureRate": 0.9355,
+        "failureRate": 0.9394,
         "framework": "vllm_tokenizer_patch",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 2,
-        "successRate": 0.0645,
+        "successRate": 0.0606,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 31,
+        "total": 33,
         "unresolvedFailureCount": 12
       },
       "Ascend_910-b3|vllm|text-generation": {
@@ -4869,36 +4890,36 @@
         "unresolvedFailureCount": 134
       },
       "vllm_tokenizer_patch": {
-        "attributableFailureCount": 32,
+        "attributableFailureCount": 34,
-        "decisionFailureRate": 0.9412,
+        "decisionFailureRate": 0.9444,
-        "decisionSuccessRate": 0.0588,
+        "decisionSuccessRate": 0.0556,
-        "decisionTotal": 34,
+        "decisionTotal": 36,
         "failureBreakdown": {
           "ambiguous_runtime": 32,
-          "framework_architecture_unsupported": 31,
+          "framework_architecture_unsupported": 33,
           "model_load": 1
         },
-        "failureCount": 64,
+        "failureCount": 66,
-        "failureRate": 0.9697,
+        "failureRate": 0.9706,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 2,
-        "successRate": 0.0303,
+        "successRate": 0.0294,
-        "total": 66,
+        "total": 68,
         "unresolvedFailureCount": 32
       }
     },
-    "generatedAt": "2026-09-20T20:09:42.279828+00:00",
+    "generatedAt": "2026-09-20T20:16:41.495864+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
-        "attributableFailureCount": 79,
+        "attributableFailureCount": 81,
-        "decisionFailureRate": 0.8061,
+        "decisionFailureRate": 0.81,
-        "decisionSuccessRate": 0.1939,
+        "decisionSuccessRate": 0.19,
-        "decisionTotal": 98,
+        "decisionTotal": 100,
         "failureBreakdown": {
           "ambiguous_runtime": 68,
-          "framework_architecture_unsupported": 75,
+          "framework_architecture_unsupported": 77,
           "memory_capacity": 1,
           "repository_structure": 1,
           "tokenizer_compatibility": 2,
@@ -4906,14 +4927,14 @@
           "日志缺失": 3,
           "验证失败": 27
         },
-        "failureCount": 196,
+        "failureCount": 198,
-        "failureRate": 0.9116,
+        "failureRate": 0.9124,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 19,
-        "successRate": 0.0884,
+        "successRate": 0.0876,
-        "total": 215,
+        "total": 217,
         "unresolvedFailureCount": 117
       },
       "Ascend_910-b4": {
@@ -5319,7 +5340,7 @@
       "hygon_k100-ai": 64.0
     },
     "pendingRecords": 0,
-    "policyCancelledRecords": 135,
+    "policyCancelledRecords": 144,
     "profileCombinationStats": {
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|cohere2|none": {
         "attributableFailureCount": 0,
@@ -5549,6 +5570,29 @@
         "total": 3,
         "unresolvedFailureCount": 0
       },
+      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_tokenizer_patch",
+        "modelType": "qwen3_5_moe",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Ascend_910-b3",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
         "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
@@ -5619,14 +5663,14 @@
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
-        "attributableFailureCount": 4,
+        "attributableFailureCount": 5,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 4,
+        "decisionTotal": 5,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 4
+          "framework_architecture_unsupported": 5
         },
-        "failureCount": 4,
+        "failureCount": 5,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "modelType": "qwen3_5",
@@ -5638,7 +5682,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 4,
+        "total": 5,
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none": {
@@ -12382,17 +12426,17 @@
         "unresolvedFailureCount": 2
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
-        "attributableFailureCount": 2,
+        "attributableFailureCount": 4,
-        "consecutiveFailures": 2,
+        "consecutiveFailures": 4,
         "consecutivePlatformFailures": 0,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 2,
+        "decisionTotal": 4,
         "failureBreakdown": {
           "ambiguous_runtime": 5,
-          "framework_architecture_unsupported": 2
+          "framework_architecture_unsupported": 4
         },
-        "failureCount": 7,
+        "failureCount": 9,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "lastPlatformFailureAt": null,
@@ -12404,7 +12448,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 7,
+        "total": 9,
         "unresolvedFailureCount": 5
       },
       "Ascend_910-b3|vllm|text-generation": {
@@ -12566,18 +12610,18 @@
         "unresolvedFailureCount": 3
       },
       "Cambricon_mlu-370-x4|unknown|text-generation": {
-        "attributableFailureCount": 6,
+        "attributableFailureCount": 5,
         "consecutiveFailures": 3,
         "consecutivePlatformFailures": 0,
-        "decisionFailureRate": 0.8571,
+        "decisionFailureRate": 0.8333,
-        "decisionSuccessRate": 0.1429,
+        "decisionSuccessRate": 0.1667,
-        "decisionTotal": 7,
+        "decisionTotal": 6,
         "failureBreakdown": {
-          "ambiguous_runtime": 3,
+          "ambiguous_runtime": 2,
-          "framework_architecture_unsupported": 6
+          "framework_architecture_unsupported": 5
         },
-        "failureCount": 9,
+        "failureCount": 7,
-        "failureRate": 0.9,
+        "failureRate": 0.875,
         "framework": "unknown",
         "lastPlatformFailureAt": null,
         "lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
@@ -12585,11 +12629,11 @@
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 1,
-        "successRate": 0.1,
+        "successRate": 0.125,
         "targetGpu": "Cambricon_mlu-370-x4",
         "taskType": "text-generation",
-        "total": 10,
+        "total": 8,
-        "unresolvedFailureCount": 3
+        "unresolvedFailureCount": 2
       },
       "Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
         "attributableFailureCount": 0,
@@ -13322,7 +13366,7 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
-      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
+      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
         "attributableFailureCount": 1,
         "consecutiveFailures": 1,
         "decisionFailureRate": 1.0,
@@ -13334,8 +13378,8 @@
         "failureCount": 1,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
-        "lastTerminalAt": "2026-09-20T16:54:50.062693+00:00",
+        "lastTerminalAt": "2026-09-20T20:16:30.961259+00:00",
-        "modelType": "qwen3_5",
+        "modelType": "qwen3_5_moe",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
@@ -13347,6 +13391,31 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
+        "attributableFailureCount": 2,
+        "consecutiveFailures": 2,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 2,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 2
+        },
+        "failureCount": 2,
+        "failureRate": 1.0,
+        "framework": "vllm_tokenizer_patch",
+        "lastTerminalAt": "2026-09-20T20:16:30.961280+00:00",
+        "modelType": "qwen3_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Ascend_910-b3",
+        "taskType": "text-generation",
+        "total": 2,
+        "unresolvedFailureCount": 0
+      },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none": {
         "attributableFailureCount": 1,
         "consecutiveFailures": 1,
@@ -15985,6 +16054,30 @@
         "total": 3,
         "unresolvedFailureCount": 0
       },
+      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|33": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_tokenizer_patch",
+        "loadSizeLog2Bucket": 33,
+        "modelType": "qwen3_5_moe",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Ascend_910-b3",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -16130,14 +16223,14 @@
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": {
-        "attributableFailureCount": 2,
+        "attributableFailureCount": 3,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 2,
+        "decisionTotal": 3,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 2
+          "framework_architecture_unsupported": 3
         },
-        "failureCount": 2,
+        "failureCount": 3,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "loadSizeLog2Bucket": 34,
@@ -16150,7 +16243,7 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 3,
         "unresolvedFailureCount": 0
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none|34": {
@@ -26034,20 +26127,20 @@
         "unresolvedFailureCount": 1
       }
     },
-    "terminalRecords": 15946,
+    "terminalRecords": 15948,
-    "totalRecords": 16081,
+    "totalRecords": 16092,
     "totals": {
-      "attributableFailureCount": 5792,
+      "attributableFailureCount": 5794,
-      "decisionFailureRate": 0.8615,
+      "decisionFailureRate": 0.8616,
-      "decisionSuccessRate": 0.1385,
+      "decisionSuccessRate": 0.1384,
-      "decisionTotal": 6723,
+      "decisionTotal": 6725,
       "failureBreakdown": {
         "ambiguous_runtime": 3799,
         "architecture_compatibility": 212,
         "attention_backend": 1,
         "backend_operator": 102,
         "context_length": 318,
-        "framework_architecture_unsupported": 2007,
+        "framework_architecture_unsupported": 2009,
         "memory_capacity": 1196,
         "model_load": 484,
         "platform_infrastructure": 922,
@@ -26058,14 +26151,14 @@
         "日志缺失": 719,
         "验证失败": 673
       },
-      "failureCount": 15015,
+      "failureCount": 15017,
       "failureRate": 0.9416,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 922,
       "successCount": 931,
       "successRate": 0.0584,
-      "total": 15946,
+      "total": 15948,
       "unresolvedFailureCount": 8301
     },
     "warnings": [
@@ -26117,6 +26210,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 16081,
+  "summarizedRecords": 16092,
   "version": 1
 }

.modelhub_state/queue_cleanup_latest.json

@@ -14,13 +14,13 @@
     100
   ],
   "accounts": 12,
-  "activeScanned": 1179,
+  "activeScanned": 1176,
   "ageCleanupMode": "admission_only",
   "agePolicySkipped": {
     "cleanupDisabled": true,
     "reason": "admission_only"
   },
-  "architectureBlockCount": 106,
+  "architectureBlockCount": 107,
   "architectureFrameworkCatalog": {
     "ascend_910-b3|text-generation": [
       "llamacpp",
@@ -67,27 +67,195 @@
     ]
   },
   "architectureFrameworkCatalogErrors": {},
-  "architectureIncompatibleCount": 1,
+  "architectureIncompatibleCount": 9,
   "architectureIncompatibleTasks": [
     {
-      "accountIndex": 3,
+      "accountIndex": 1,
       "architectureBlockEvidenceCount": 1,
-      "architectureBlockExpiresAt": "2026-10-20T02:52:51.740561+00:00",
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
       "architectureMatchScope": "exact_framework",
       "architectureMatchType": "model_type",
-      "architectureSignature": "model_type:qwen3_vl",
+      "architectureSignature": "model_type:qwen3_5_moe",
       "architectureSignatures": [
-        "model_type:qwen3_vl"
+        "model_type:qwen3_5_moe"
       ],
       "evaluatedFrameworks": [
         "vllm_tokenizer_patch"
       ],
       "framework": "vllm_tokenizer_patch",
       "gpuType": "Ascend_910-b3",
-      "modelId": "BAAI/RoboBrain2.5-8B-NV",
+      "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
       "reason": "known_framework_architecture_incompatible",
       "status": "waiting",
-      "taskId": 4969052,
+      "taskId": 4857813,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 1,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4923523,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 3,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4857814,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 5,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4795478,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 6,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "primitive-ai/Nex-N2.5-mini-FP8",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4753715,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "Edge0/Edge0-35B-A3B-preview",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4845402,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4938618,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 8,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4845403,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 9,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4969061,
       "taskType": "text-generation"
     }
   ],
@@ -113,29 +281,29 @@
     "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": 65,
+  "architectureModelConfigsComplete": 64,
   "architectureOnly": true,
   "architecturePolicySkipped": {
     "frameworkCatalogUnknown": 0,
-    "frameworkContextUnknown": 79,
+    "frameworkContextUnknown": 78,
     "modelArchitectureUnknown": 134,
-    "noMatchingBlock": 1021,
+    "noMatchingBlock": 1010,
     "partiallyBlockedFrameworkSet": 23,
     "runningMatchedProtected": 0,
     "submissionContextMismatch": 0,
     "submissionContextUnknown": 0
   },
-  "cancelledCount": 1,
+  "cancelledCount": 9,
   "cancelledTasks": [
     {
-      "accountIndex": 3,
+      "accountIndex": 1,
       "architectureBlockEvidenceCount": 1,
-      "architectureBlockExpiresAt": "2026-10-20T02:52:51.740561+00:00",
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
       "architectureMatchScope": "exact_framework",
       "architectureMatchType": "model_type",
-      "architectureSignature": "model_type:qwen3_vl",
+      "architectureSignature": "model_type:qwen3_5_moe",
       "architectureSignatures": [
-        "model_type:qwen3_vl"
+        "model_type:qwen3_5_moe"
       ],
       "cleanupReasons": [
         "known_framework_architecture_incompatible"
@@ -145,16 +313,208 @@
       ],
       "framework": "vllm_tokenizer_patch",
       "gpuType": "Ascend_910-b3",
-      "modelId": "BAAI/RoboBrain2.5-8B-NV",
+      "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
       "reason": "known_framework_architecture_incompatible",
       "status": "waiting",
-      "taskId": 4969052,
+      "taskId": 4857813,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 1,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4923523,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 3,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4857814,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 5,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4795478,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 6,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "primitive-ai/Nex-N2.5-mini-FP8",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4753715,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "Edge0/Edge0-35B-A3B-preview",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4845402,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4938618,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 8,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4845403,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 9,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-10-20T02:52:51.748956+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5_moe",
+      "architectureSignatures": [
+        "model_type:qwen3_5_moe"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm_tokenizer_patch"
+      ],
+      "framework": "vllm_tokenizer_patch",
+      "gpuType": "Ascend_910-b3",
+      "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 4969061,
       "taskType": "text-generation"
     }
   ],
   "certainOomCount": 0,
   "certainOomTasks": [],
-  "cleanupCandidateCount": 1,
+  "cleanupCandidateCount": 9,
   "dryRun": false,
   "listingErrors": {},
   "modelAgeErrors": {},
@@ -179,7 +539,7 @@
   ],
   "oldOverflowCount": 0,
   "oldOverflowTasks": [],
-  "policyCancelledRecorded": 1,
+  "policyCancelledRecorded": 9,
   "policyNoLongerAppliesCount": 0,
   "policyNoLongerAppliesTasks": [],
   "recentModelDays": 7,
@@ -192,5 +552,5 @@
     "repositorySizeUnknown": 0
   },
   "stopErrors": [],
-  "uniqueModels": 342
+  "uniqueModels": 341
 }

.modelhub_state/recent_outcomes.jsonl

@@ -133,6 +133,8 @@
 {"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T19:56:29.962443+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.939142+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969070", "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", "failureUnsupportedArchitectures": ["Cohere2ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266177+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730845002, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730845002}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.937617+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969071", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T16:44:23.353846+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.842110+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969064", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T20:16:30.961259+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T02:52:51.748956+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969058", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T20:16:30.961280+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 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": "2026-09-20T02:52:51.741993+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969059", "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_vl"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:09:29.752180+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.740561+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969062", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T17:09:45.266185+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T02:52:51.693959+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969057", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T16:54:50.062693+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "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": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.682339+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969056", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
 {"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": "2026-09-15T03:19:58.951204+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T03:13:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609100", "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": "2026-09-15T03:19:58.951164+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T03:11:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609085", "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": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T03:10:10.823457+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T03:05:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4592335", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-15T01:43:44.814965+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4570941", "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": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T01:43:44.814946+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4591253", "taskType": "text-generation", "verifyResult": -1}

.modelhub_state/recovery_intents.jsonl

@@ -1806,6 +1806,18 @@
 {"batchId": "cd7e8ec006ed4518b2c7bbea62e578e7", "completedAt": "2026-09-20T20:09:24.578625+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:09:22.950262+00:00", "framework": "transformers", "intentId": "cb8eab032eff4ad889e43272ab9b70c2", "lastModified": "2026-09-16T17:13:44+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "reason": null, "reconciledAt": "2026-09-20T20:13:11.719972+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation"}
 {"batchId": "cd7e8ec006ed4518b2c7bbea62e578e7", "completedAt": "2026-09-20T20:09:24.578631+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:09:22.950385+00:00", "framework": "transformers", "intentId": "9b1e75d077514f818695965b3dcf3333", "lastModified": "2026-09-15T15:11:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-20T20:13:11.719969+00:00", "repoId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation"}
 {"batchId": "cd7e8ec006ed4518b2c7bbea62e578e7", "completedAt": "2026-09-20T20:09:24.578639+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:09:22.950568+00:00", "framework": "transformers", "intentId": "91f04ef9a08944d2b0fb04599a84b5f5", "lastModified": "2026-09-16T17:28:41+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-8bit", "reason": null, "reconciledAt": "2026-09-20T20:13:11.719450+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-100", "taskId": "4986875", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803370+00:00", "framework": "transformers", "intentId": "533bc66337d34d66829770f562798d15", "lastModified": "2026-09-18T05:43:55+00:00", "modelAddress": "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "repoId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803500+00:00", "framework": "transformers", "intentId": "226e69cc9a3b4d548b51511ea1148f1e", "lastModified": "2026-09-16T16:38:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-4-12B-it-FP8-Dynamic", "repoId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803567+00:00", "framework": "transformers", "intentId": "3bf43846c73244e4ac239657527456fe", "lastModified": "2026-09-17T08:53:56+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-35B-A3B-preview", "repoId": "Edge0/Edge0-35B-A3B-preview", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803630+00:00", "framework": "transformers", "intentId": "e4860d273544430d835f1c8b65e3adbb", "lastModified": "2026-09-14T10:29:22+00:00", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "repoId": "hcnote/SparkMuse-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803701+00:00", "framework": "transformers", "intentId": "bdb5184c37054c03a4221374a789476b", "lastModified": "2026-09-17T08:55:16+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "repoId": "Edge0/Edge0-8B-A1B-preview", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803764+00:00", "framework": "transformers", "intentId": "8c608c35649e4d539c9c787faf37c369", "lastModified": "2026-09-14T09:13:00+00:00", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT8", "repoId": "hcnote/SparkMuse-4B-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803826+00:00", "framework": "transformers", "intentId": "0db6e497759c476e818c4af181a35fd0", "lastModified": "2026-09-14T13:41:18+00:00", "modelAddress": "https://modelscope.cn/models/yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "repoId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803888+00:00", "framework": "transformers", "intentId": "8d27f8ed2e0446919e4a5efdf2b44e4a", "lastModified": "2026-09-15T15:20:58+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.803949+00:00", "framework": "transformers", "intentId": "1e324beca6b844f9b4a64cfbca68d430", "lastModified": "2026-09-15T15:16:38+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.804010+00:00", "framework": "transformers", "intentId": "5c0f6acd424c4142b3514b962a7eaa31", "lastModified": "2026-09-15T15:22:00+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.804072+00:00", "framework": "transformers", "intentId": "83febeee331f473aab453aaba5f7f135", "lastModified": "2026-09-15T15:24:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
+{"batchId": "e8d1e58fcad44bfca0e75cc52bf8640a", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:16:41.804133+00:00", "framework": "transformers", "intentId": "31f3cbb2871c42e69713d8730f2afa72", "lastModified": "2026-09-16T16:32:52+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-7B-FP8", "repoId": "IFM/K2-Horizon-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation"}
 {"batchId": "24fc3f986e8d444c9b098e7a0ff64990", "completedAt": "2026-09-20T20:15:29.939209+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:15:28.941919+00:00", "framework": "transformers", "intentId": "87224a5987ff47518bb67b8451c65185", "repoId": "IFM/K2-Horizon-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "framework_prerequisite_deferred", "targetGpu": "Iluvatar_bi-100", "taskId": null, "taskType": "text-generation"}
 {"batchId": "24fc3f986e8d444c9b098e7a0ff64990", "completedAt": "2026-09-20T20:15:29.939206+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:15:28.941858+00:00", "framework": "transformers", "intentId": "7038445dff7d45e2b21a946d6c248f71", "repoId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "framework_prerequisite_deferred", "targetGpu": "Iluvatar_bi-100", "taskId": null, "taskType": "text-generation"}
 {"batchId": "24fc3f986e8d444c9b098e7a0ff64990", "completedAt": "2026-09-20T20:15:29.939204+00:00", "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configSource": "modelhub_live", "createdAt": "2026-09-20T20:15:28.941796+00:00", "framework": "transformers", "intentId": "ce6fc81a7c6346d198ce3bd75cc3e345", "repoId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "framework_prerequisite_deferred", "targetGpu": "Iluvatar_bi-100", "taskId": null, "taskType": "text-generation"}

manifest.json

@@ -1,24 +1,24 @@
 {
   "agentVersion": "2026.09.20.2",
   "checksums": {
-    ".modelhub_state/architecture_compatibility_blacklist.json": "8880c9aac31e582a779a343d55d019dddf979f44fc233a11924f295451a291e3",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "a187bb816097eb61019b6c7b28e6a5b5c87965782a74ea40b3c1c0617da66653",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "802ede2066d64599cf0498321ec02f4dce9741121c3c37a029204f18b4692496",
+    ".modelhub_state/market_intelligence.json": "0d60dadf7e659a4d6c437a27c6e5cebdff50b49455ef42b970da527b962b3b92",
-    ".modelhub_state/official_capabilities.json": "7bd9f6f8ae5c37b6775dff129cb005d20e53d4b61eb7ea120120840100ab4b7a",
+    ".modelhub_state/official_capabilities.json": "014e08dbb30856cf7b28deb05460007af3cc0a0f48b91a515cd9ac0b2f6388be",
-    ".modelhub_state/outcome_checkpoint.json": "eece9db0e52a5d969c2d1e33332d1c3cf610d0ea51da97e7173f26e8cd15fb88",
+    ".modelhub_state/outcome_checkpoint.json": "a830fd1e3c9e2e3fc0731321568c63a8bbc700551ad8ee9fe886e0f67143d929",
-    ".modelhub_state/queue_cleanup_latest.json": "5c13f2f8897b2c666003846b350d4936c333a5667a4868e7bb80a2152e0ef233",
+    ".modelhub_state/queue_cleanup_latest.json": "6c568eedbdb320ab86862ab3e7b8656f22369b3626cca47fb8c18d92ad18f82d",
-    ".modelhub_state/recent_outcomes.jsonl": "6ee261acbe5709629bf7d9b02ab8aaaf98a764786831a6fa85c8c8b031058b5d",
+    ".modelhub_state/recent_outcomes.jsonl": "5e63e5072004dadc5ec6ce62b76e6f7e0ba7c486d37af4f9a25ba7d86b9d40d5",
     ".modelhub_state/recovery_active_tasks.jsonl": "69e2a1131f279c8b7811ce1829a1af29b3a30f4afb9544484ce84ed680dd2939",
-    ".modelhub_state/recovery_intents.jsonl": "6de026ca2ed7b4f7363b745ec298c95ba0e28b3042c61fc7d946ccf6d4285acc",
+    ".modelhub_state/recovery_intents.jsonl": "8327f7687f32270386d1e2d0dbc2a8b6c8f21db6bd0c149f8307d376c487e09f",
     ".modelhub_state/routing_intelligence.json": "1f8aadf439f3f724e676be3f02d42f19616158c24a616f0f9fd340f5c60b8993",
     ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
     ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
     "ledger/submissions.jsonl": "4d7b0732e883a63b74956e057eb85c1ecedde0e8ca715af9b3a27fa4ce6f9edf",
-    "outcomes/submissions.jsonl": "0e8e09602ad376bd98798c84f36d64f6d0faef38b95b39b639515257a6e68da3"
+    "outcomes/submissions.jsonl": "bc3c2c94411f747146cec2b8e39f57423f383b0b7f6b4441f50b5e0bd0374c5e"
   },
-  "generation": 10878,
+  "generation": 10879,
-  "phase": "result",
+  "phase": "intent",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-20T20:15:30.115970+00:00",
+  "updatedAt": "2026-09-20T20:16:41.936815+00:00",
   "writerId": "fc715c06e24c4db2ae3e425e435db996"
 }

outcomes/submissions.jsonl

@@ -139,7 +139,6 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454482+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.107121+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749470", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454474+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.105705+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749471", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T13:14:20.004672+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:13:27.470794+00:00", "targetGpu": "Vastai_va16", "taskId": "4753071", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004674+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.452554+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753715", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T13:55:40.785159+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1764a9124cd000c7904ba9cee10ecdf5f9bfd4e65fc6896e0120a683f5e606e3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607039+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.442486+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754066", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607077+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.435840+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation", "verifyResult": null}
@@ -192,7 +191,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T09:26:00.311239+00:00", "modelId": "nex-agi/Nex-N2.5-mini", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214494016, "estimatedRequiredGiB": 78.495, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70235999301, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 70235999301}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T01:22:51.908714+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791410", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318710+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.116897+00:00", "targetGpu": "Biren_166m", "taskId": "4794241", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318700+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "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, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.114996+00:00", "targetGpu": "Biren_166m", "taskId": "4794242", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T14:23:18.821537+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:19:56.330927+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316548+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316560+00:00", "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T22:16:38.428761+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "verifyResult": null}
@@ -221,8 +219,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525004+00:00", "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903777808, "estimatedRequiredGiB": 80.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71923892164, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:huihui", "custom_tag:offensive-security", "custom_tag:pentesting", "custom_tag:tool-calling", "custom_tag:cyberstrike", "custom_tag:qwen3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71923892164}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T15:20:07.717928+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "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": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:16:07.103690+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4845112", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:20:07.717905+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:16:07.108792+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4845111", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T15:38:36.096895+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:34:50.109255+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4845402", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T15:38:36.096917+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:34:50.118234+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4845403", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-14T15:57:15.747158+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:52:17.993254+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4845635", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-14T15:57:15.747166+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:54:31.201810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4845679", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-14T16:27:14.009107+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "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": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T08:26:23.557278+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4846122", "taskType": "text-generation", "verifyResult": null}
@@ -253,8 +249,6 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T05:25:28.408813+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "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": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:17:59.038422+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4857428", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803008+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.586588+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857632", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803064+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.589018+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857633", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:54:37.536102+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:47:17.029854+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857814", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:54:37.536172+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:47:17.027666+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857813", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T06:16:21.605496+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "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": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:08:21.049320+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4858026", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T06:16:21.605550+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "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": 13269529266, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:08:21.042712+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4858025", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-15T07:00:32.211851+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T22:58:26.649925+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860053", "taskType": "text-generation", "verifyResult": null}
@@ -358,7 +352,6 @@
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-18T01:30:42.351661+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T17:28:00.659090+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920239", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-18T01:42:51.866260+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "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:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T17:38:48.679382+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920434", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-18T05:46:07.695608+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "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": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T21:45:54.233698+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4923309", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-18T06:05:49.190180+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:03:22.715585+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4923523", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-18T06:24:52.891825+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "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": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:21:10.450004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4923702", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T07:01:53.813894+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T22:55:35.549905+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4924043", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T07:20:15.618254+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T23:13:41.953804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4924273", "taskType": "text-generation", "verifyResult": null}
@@ -391,7 +384,6 @@
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:01:59.403449+00:00", "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "prism_hadamard_qwen35", "modelscopeFileSize": 8608734989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2589078768, "modelscopeTags": ["license:apache-2.0", "model_type:prism_hadamard_qwen35", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:mlx", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8608734989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:56:47.451096+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938210", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:01:59.403510+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:56:47.449292+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938209", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-19T02:19:07.486735+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:17:22.750439+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4938406", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-19T02:36:05.598906+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:34:31.787488+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4938618", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:44:40.297028+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-19T03:01:51.490259+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:58:28.435554+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-19T03:45:21.131949+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T19:38:31.546614+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "taskType": "text-generation", "verifyResult": null}
@@ -477,10 +469,7 @@
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647775+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.536043+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969046", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647490+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "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", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.643751+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969053", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647352+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.575551+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969051", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647769+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24651300904, "estimatedRequiredGiB": 27.587, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24684544516, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 24684544516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.738447+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969061", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647874+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 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": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.741993+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969059", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647543+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "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": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.691589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969060", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647460+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.748956+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969058", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647485+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34327989512, "estimatedRequiredGiB": 38.385, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 34346039951, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 34346039951}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.844248+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969066", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647678+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "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": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.846373+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969063", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647403+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-09-20T02:52:51.852389+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969067", "taskType": "text-generation", "verifyResult": null}
@@ -955,8 +944,8 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:56:29.962409+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299919, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299919}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:52:06.534997+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978249", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "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": 9093251763, "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": 9093251763}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:54:11.089175+00:00", "targetGpu": "Biren_166m", "taskId": "4978283", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:13:01.970350+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860632064, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860632064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:12:07.582993+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978470", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:12:07.735021+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978493", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T20:16:30.961272+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:12:07.735021+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978493", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367933, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367933}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:13:32.801809+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978494", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:16:30.961235+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367933, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367933}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:13:32.801809+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978494", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "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", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:20:00.435973+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4978589", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720441937, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720441937}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:20:08.512684+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4978597", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "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", "repositoryOnDiskBytes": 16568142341}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T12:20:14.952760+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978600", "taskType": "text-generation", "verifyResult": null}