state: generation 21687 (intent)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -1288,6 +1288,25 @@
       "targetGpu": "hygon_k100-ai",
       "taskType": "text-generation"
     },
+    "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5": {
+      "architectureSignature": "model_type:qwen3_5",
+      "architectures": [],
+      "evidenceCount": 1,
+      "expiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "framework": "vllm-patch-tokenizer",
+      "latestFailureAt": "2026-10-06T09:15:23.045201+00:00",
+      "latestSuccessfulAt": null,
+      "matchType": "model_type",
+      "modelType": "qwen3_5",
+      "sourceModelIds": [
+        "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw"
+      ],
+      "sourceTaskIds": [
+        "5320526"
+      ],
+      "targetGpu": "hygon_k100-ai",
+      "taskType": "text-generation"
+    },
     "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5_moe": {
       "architectureSignature": "model_type:qwen3_5_moe",
       "architectures": [],
@@ -2779,9 +2798,9 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-07T03:30:07.043765+00:00",
+  "generatedAt": "2026-10-07T03:40:16.204864+00:00",
   "summary": {
-    "activeBlockCount": 140,
+    "activeBlockCount": 141,
     "byGpuFramework": {
       "Ascend_910-b3|vllm": 9,
       "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2806,7 +2825,7 @@
       "Vastai_va16|vllm": 13,
       "Vastai_va16|vllm_fix_tokenizer": 2,
       "hygon_k100-ai|vllm": 8,
-      "hygon_k100-ai|vllm-patch-tokenizer": 3
+      "hygon_k100-ai|vllm-patch-tokenizer": 4
     },
     "ttlDays": 30
   }

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-07T03:36:58.603226+00:00",
+  "generatedAt": "2026-10-07T03:43:43.538441+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-07T01:55:18.403270+00:00",
+  "generatedAt": "2026-10-07T03:43:43.438594+00:00",
-  "lastSyncTime": "2026-10-07T01:55:18.170081+00:00",
+  "lastSyncTime": "2026-10-07T03:43:43.371873+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -1292,6 +1292,25 @@
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation"
       },
+      "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5": {
+        "architectureSignature": "model_type:qwen3_5",
+        "architectures": [],
+        "evidenceCount": 1,
+        "expiresAt": "2026-11-05T09:15:23.045201+00:00",
+        "framework": "vllm-patch-tokenizer",
+        "latestFailureAt": "2026-10-06T09:15:23.045201+00:00",
+        "latestSuccessfulAt": null,
+        "matchType": "model_type",
+        "modelType": "qwen3_5",
+        "sourceModelIds": [
+          "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw"
+        ],
+        "sourceTaskIds": [
+          "5320526"
+        ],
+        "targetGpu": "hygon_k100-ai",
+        "taskType": "text-generation"
+      },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5_moe": {
         "architectureSignature": "model_type:qwen3_5_moe",
         "architectures": [],
@@ -2784,7 +2803,7 @@
       }
     },
     "architectureCompatibilitySummary": {
-      "activeBlockCount": 140,
+      "activeBlockCount": 141,
       "byGpuFramework": {
         "Ascend_910-b3|vllm": 9,
         "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2809,7 +2828,7 @@
         "Vastai_va16|vllm": 13,
         "Vastai_va16|vllm_fix_tokenizer": 2,
         "hygon_k100-ai|vllm": 8,
-        "hygon_k100-ai|vllm-patch-tokenizer": 3
+        "hygon_k100-ai|vllm-patch-tokenizer": 4
       },
       "ttlDays": 30
     },
@@ -2907,25 +2926,25 @@
         "decisionSuccessRate": 0.0784,
         "decisionTotal": 51,
         "failureBreakdown": {
-          "ambiguous_runtime": 92,
+          "ambiguous_runtime": 93,
           "context_length": 9,
           "framework_architecture_unsupported": 37,
           "memory_capacity": 1,
           "platform_infrastructure": 1,
           "参数/模板问题": 8
         },
-        "failureCount": 148,
+        "failureCount": 149,
-        "failureRate": 0.9737,
+        "failureRate": 0.9739,
         "framework": "vllm_tokenizer_patch",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 4,
-        "successRate": 0.0263,
+        "successRate": 0.0261,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 152,
+        "total": 153,
-        "unresolvedFailureCount": 100
+        "unresolvedFailureCount": 101
       },
       "Ascend_910-b3|vllm|text-generation": {
         "attributableFailureCount": 71,
@@ -5302,19 +5321,19 @@
         "unresolvedFailureCount": 72
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
-        "attributableFailureCount": 62,
+        "attributableFailureCount": 63,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 62,
+        "decisionTotal": 63,
         "failureBreakdown": {
           "ambiguous_runtime": 47,
-          "framework_architecture_unsupported": 24,
+          "framework_architecture_unsupported": 25,
           "model_load": 14,
           "repository_structure": 5,
           "runtime_memory": 19,
           "参数/模板问题": 11
         },
-        "failureCount": 120,
+        "failureCount": 121,
         "failureRate": 1.0,
         "framework": "vllm-patch-tokenizer",
         "pendingCount": 0,
@@ -5324,7 +5343,7 @@
         "successRate": 0.0,
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation",
-        "total": 120,
+        "total": 121,
         "unresolvedFailureCount": 58
       },
       "hygon_k100-ai|vllm|text-generation": {
@@ -5558,26 +5577,26 @@
         "unresolvedFailureCount": 109
       },
       "vllm-patch-tokenizer": {
-        "attributableFailureCount": 62,
+        "attributableFailureCount": 63,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 62,
+        "decisionTotal": 63,
         "failureBreakdown": {
           "ambiguous_runtime": 47,
-          "framework_architecture_unsupported": 24,
+          "framework_architecture_unsupported": 25,
           "model_load": 14,
           "repository_structure": 5,
           "runtime_memory": 19,
           "参数/模板问题": 11
         },
-        "failureCount": 120,
+        "failureCount": 121,
         "failureRate": 1.0,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 0,
         "successRate": 0.0,
-        "total": 120,
+        "total": 121,
         "unresolvedFailureCount": 58
       },
       "vllm_0_17_0_corex_4_4_0": {
@@ -5635,7 +5654,7 @@
         "decisionSuccessRate": 0.0625,
         "decisionTotal": 160,
         "failureBreakdown": {
-          "ambiguous_runtime": 207,
+          "ambiguous_runtime": 208,
           "backend_operator": 15,
           "context_length": 9,
           "framework_architecture_unsupported": 93,
@@ -5647,18 +5666,18 @@
           "tokenizer_compatibility": 2,
           "参数/模板问题": 29
         },
-        "failureCount": 389,
+        "failureCount": 390,
-        "failureRate": 0.9749,
+        "failureRate": 0.975,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 3,
         "successCount": 10,
-        "successRate": 0.0251,
+        "successRate": 0.025,
-        "total": 399,
+        "total": 400,
-        "unresolvedFailureCount": 236
+        "unresolvedFailureCount": 237
       }
     },
-    "generatedAt": "2026-10-07T01:55:18.386532+00:00",
+    "generatedAt": "2026-10-07T03:43:43.422414+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 119,
@@ -5666,7 +5685,7 @@
         "decisionSuccessRate": 0.156,
         "decisionTotal": 141,
         "failureBreakdown": {
-          "ambiguous_runtime": 161,
+          "ambiguous_runtime": 162,
           "context_length": 9,
           "framework_architecture_unsupported": 104,
           "memory_capacity": 2,
@@ -5677,15 +5696,15 @@
           "日志缺失": 3,
           "验证失败": 27
         },
-        "failureCount": 351,
+        "failureCount": 352,
-        "failureRate": 0.941,
+        "failureRate": 0.9412,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 22,
-        "successRate": 0.059,
+        "successRate": 0.0588,
-        "total": 373,
+        "total": 374,
-        "unresolvedFailureCount": 231
+        "unresolvedFailureCount": 232
       },
       "Ascend_910-b4": {
         "attributableFailureCount": 331,
@@ -6051,16 +6070,16 @@
         "unresolvedFailureCount": 1322
       },
       "hygon_k100-ai": {
-        "attributableFailureCount": 742,
+        "attributableFailureCount": 743,
-        "decisionFailureRate": 0.9537,
+        "decisionFailureRate": 0.9538,
-        "decisionSuccessRate": 0.0463,
+        "decisionSuccessRate": 0.0462,
-        "decisionTotal": 778,
+        "decisionTotal": 779,
         "failureBreakdown": {
           "ambiguous_runtime": 345,
           "architecture_compatibility": 32,
           "attention_backend": 1,
           "context_length": 46,
-          "framework_architecture_unsupported": 256,
+          "framework_architecture_unsupported": 257,
           "memory_capacity": 59,
           "model_load": 74,
           "platform_infrastructure": 4,
@@ -6071,14 +6090,14 @@
           "日志缺失": 66,
           "验证失败": 27
         },
-        "failureCount": 1576,
+        "failureCount": 1577,
         "failureRate": 0.9777,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 4,
         "successCount": 36,
         "successRate": 0.0223,
-        "total": 1612,
+        "total": 1613,
         "unresolvedFailureCount": 830
       }
     },
@@ -6099,7 +6118,7 @@
       "hygon_k100-ai": 64.0
     },
     "pendingRecords": 0,
-    "policyCancelledRecords": 224,
+    "policyCancelledRecords": 237,
     "profileCombinationStats": {
       "Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
         "attributableFailureCount": 0,
@@ -6173,9 +6192,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 13
+          "ambiguous_runtime": 14
         },
-        "failureCount": 13,
+        "failureCount": 14,
         "failureRate": 1.0,
         "framework": "vllm_tokenizer_patch",
         "modelType": "gemma2",
@@ -6187,8 +6206,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 13,
+        "total": 14,
-        "unresolvedFailureCount": 13
+        "unresolvedFailureCount": 14
       },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": {
         "attributableFailureCount": 0,
@@ -24322,14 +24341,14 @@
         "unresolvedFailureCount": 0
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none": {
-        "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-patch-tokenizer",
         "modelType": "qwen3_5",
@@ -24341,7 +24360,7 @@
         "successRate": 0.0,
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 3,
         "unresolvedFailureCount": 0
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_vl|none": {
@@ -25034,9 +25053,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "参数/模板问题": 8
+          "参数/模板问题": 7
         },
-        "failureCount": 8,
+        "failureCount": 7,
         "failureRate": 1.0,
         "framework": "unknown",
         "lastPlatformFailureAt": null,
@@ -25048,8 +25067,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b4",
         "taskType": "text-generation",
-        "total": 8,
+        "total": 7,
-        "unresolvedFailureCount": 8
+        "unresolvedFailureCount": 7
       },
       "Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
         "attributableFailureCount": 0,
@@ -25752,22 +25771,23 @@
         "unresolvedFailureCount": 1
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
-        "attributableFailureCount": 5,
+        "attributableFailureCount": 6,
-        "consecutiveFailures": 5,
+        "consecutiveFailures": 6,
         "consecutivePlatformFailures": 0,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 5,
+        "decisionTotal": 6,
         "failureBreakdown": {
           "ambiguous_runtime": 6,
+          "framework_architecture_unsupported": 1,
           "repository_structure": 1,
           "runtime_memory": 4
         },
-        "failureCount": 11,
+        "failureCount": 12,
         "failureRate": 1.0,
         "framework": "vllm-patch-tokenizer",
         "lastPlatformFailureAt": null,
-        "lastTerminalAt": "2026-09-25T05:14:51.671721+00:00",
+        "lastTerminalAt": "2026-10-07T03:40:15.756923+00:00",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
@@ -25775,7 +25795,7 @@
         "successRate": 0.0,
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation",
-        "total": 11,
+        "total": 12,
         "unresolvedFailureCount": 6
       },
       "hygon_k100-ai|vllm|text-generation": {
@@ -29032,6 +29052,31 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none": {
+        "attributableFailureCount": 1,
+        "consecutiveFailures": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm-patch-tokenizer",
+        "lastTerminalAt": "2026-10-07T03:40:15.756923+00:00",
+        "modelType": "qwen3_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "hygon_k100-ai",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors": {
         "attributableFailureCount": 2,
         "consecutiveFailures": 2,
@@ -29249,6 +29294,30 @@
         "total": 3,
         "unresolvedFailureCount": 3
       },
+      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|34": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_tokenizer_patch",
+        "loadSizeLog2Bucket": 34,
+        "modelType": "gemma2",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "compressed-tensors",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Ascend_910-b3",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 1
+      },
       "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors|34": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -57017,14 +57086,14 @@
         "unresolvedFailureCount": 0
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|33": {
-        "attributableFailureCount": 1,
+        "attributableFailureCount": 2,
         "decisionFailureRate": 1.0,
         "decisionSuccessRate": 0.0,
-        "decisionTotal": 1,
+        "decisionTotal": 2,
         "failureBreakdown": {
-          "framework_architecture_unsupported": 1
+          "framework_architecture_unsupported": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm-patch-tokenizer",
         "loadSizeLog2Bucket": 33,
@@ -57037,7 +57106,7 @@
         "successRate": 0.0,
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|34": {
@@ -57880,20 +57949,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17353,
+    "terminalRecords": 17355,
-    "totalRecords": 17577,
+    "totalRecords": 17592,
     "totals": {
-      "attributableFailureCount": 6238,
+      "attributableFailureCount": 6239,
       "decisionFailureRate": 0.8645,
       "decisionSuccessRate": 0.1355,
-      "decisionTotal": 7216,
+      "decisionTotal": 7217,
       "failureBreakdown": {
-        "ambiguous_runtime": 4557,
+        "ambiguous_runtime": 4558,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 129,
         "context_length": 327,
-        "framework_architecture_unsupported": 2261,
+        "framework_architecture_unsupported": 2262,
         "memory_capacity": 1206,
         "model_load": 568,
         "platform_infrastructure": 952,
@@ -57904,15 +57973,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16375,
+      "failureCount": 16377,
       "failureRate": 0.9436,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 952,
       "successCount": 978,
       "successRate": 0.0564,
-      "total": 17353,
+      "total": 17355,
-      "unresolvedFailureCount": 9185
+      "unresolvedFailureCount": 9186
     },
     "warnings": [
       "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -57972,6 +58041,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17577,
+  "summarizedRecords": 17592,
   "version": 1
 }

.modelhub_state/queue_cleanup_latest.json

@@ -14,13 +14,13 @@
     100
   ],
   "accounts": 12,
-  "activeScanned": 1170,
+  "activeScanned": 1167,
   "ageCleanupMode": "admission_only",
   "agePolicySkipped": {
     "cleanupDisabled": true,
     "reason": "admission_only"
   },
-  "architectureBlockCount": 140,
+  "architectureBlockCount": 141,
   "architectureFrameworkCatalog": {
     "ascend_910-b3|text-generation": [
       "llamacpp",
@@ -33,21 +33,6 @@
       "vllm",
       "vllm_tokenizer_patch"
     ],
-    "biren_166m|text-generation": [
-      "vllm",
-      "vllm_fix_tokenizer",
-      "vllm_tokenizer_patch"
-    ],
-    "cambricon_mlu-370-x4|text-generation": [
-      "vllm",
-      "vllm-customized",
-      "vllm-mlu"
-    ],
-    "cambricon_mlu-370-x8|text-generation": [
-      "vllm",
-      "vllm-customized",
-      "vllm-mlu"
-    ],
     "hygon_k100-ai|text-generation": [
       "llamacpp",
       "vllm",
@@ -61,37 +46,294 @@
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
-    "iluvatar_mrv-100|text-generation": [
-      "transformers",
-      "vllm"
-    ],
     "kunlunxin_p-800|text-generation": [
       "vllm",
       "vllm_fix_tokenizer",
       "vllm_tokenizer_patch"
     ],
-    "metax_c-500|text-generation": [
-      "vllm",
-      "vllm_tokenizer_patch"
-    ],
     "mthreads_s4000|text-generation": [
       "llamacpp",
       "vllm",
       "vllm_tokenizer_patch"
-    ],
-    "sunrise_pt-200-x1|text-generation": [
-      "sglang",
-      "vllm",
-      "vllm_fix_tokenizer"
-    ],
-    "vastai_va16|text-generation": [
-      "vllm",
-      "vllm_fix_tokenizer"
     ]
   },
   "architectureFrameworkCatalogErrors": {},
-  "architectureIncompatibleCount": 0,
+  "architectureIncompatibleCount": 13,
-  "architectureIncompatibleTasks": [],
+  "architectureIncompatibleTasks": [
+    {
+      "accountIndex": 3,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "ukisai/Swift-1.5-5bit-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320515,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 3,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "togethercomputer/Tev1-0.8B-experimental",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320858,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 4,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320518,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 5,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320517,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 5,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "togethercomputer/Tev1-4B-experimental",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320857,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 6,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "ukisai/Swift-1.5-4bit-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320840,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320519,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320844,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320886,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 8,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320892,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 9,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320020,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 12,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320854,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 12,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "groxaxo/Hemmingway-1-oQ5-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5343702,
+      "taskType": "text-generation"
+    }
+  ],
   "architectureModelConfigErrors": {
     "GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=500)",
     "LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=500)",
@@ -114,22 +356,335 @@
     "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=500)"
   },
   "architectureModelConfigsComplete": 39,
-  "architectureOnly": false,
+  "architectureOnly": true,
   "architecturePolicySkipped": {
     "frameworkCatalogUnknown": 0,
     "frameworkContextUnknown": 44,
     "modelArchitectureUnknown": 159,
-    "noMatchingBlock": 995,
+    "noMatchingBlock": 979,
     "partiallyBlockedFrameworkSet": 16,
     "runningMatchedProtected": 0,
     "submissionContextMismatch": 0,
     "submissionContextUnknown": 0
   },
-  "cancelledCount": 0,
+  "cancelledCount": 13,
-  "cancelledTasks": [],
+  "cancelledTasks": [
+    {
+      "accountIndex": 3,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "ukisai/Swift-1.5-5bit-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320515,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 3,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "togethercomputer/Tev1-0.8B-experimental",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320858,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 4,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320518,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 5,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320517,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 5,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "togethercomputer/Tev1-4B-experimental",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320857,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 6,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "ukisai/Swift-1.5-4bit-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320840,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320519,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320844,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 7,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320886,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 8,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320892,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 9,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320020,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 12,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5320854,
+      "taskType": "text-generation"
+    },
+    {
+      "accountIndex": 12,
+      "architectureBlockEvidenceCount": 1,
+      "architectureBlockExpiresAt": "2026-11-05T09:15:23.045201+00:00",
+      "architectureMatchScope": "exact_framework",
+      "architectureMatchType": "model_type",
+      "architectureSignature": "model_type:qwen3_5",
+      "architectureSignatures": [
+        "model_type:qwen3_5"
+      ],
+      "cleanupReasons": [
+        "known_framework_architecture_incompatible"
+      ],
+      "evaluatedFrameworks": [
+        "vllm-patch-tokenizer"
+      ],
+      "framework": "vllm-patch-tokenizer",
+      "gpuType": "hygon_k100-ai",
+      "modelId": "groxaxo/Hemmingway-1-oQ5-MLX",
+      "reason": "known_framework_architecture_incompatible",
+      "status": "waiting",
+      "taskId": 5343702,
+      "taskType": "text-generation"
+    }
+  ],
   "certainOomCount": 0,
   "certainOomTasks": [],
-  "cleanupCandidateCount": 0,
+  "cleanupCandidateCount": 13,
   "dryRun": false,
   "listingErrors": {},
   "modelAgeErrors": {},
@@ -154,18 +709,18 @@
   ],
   "oldOverflowCount": 0,
   "oldOverflowTasks": [],
-  "policyCancelledRecorded": 0,
+  "policyCancelledRecorded": 13,
   "policyNoLongerAppliesCount": 0,
   "policyNoLongerAppliesTasks": [],
   "recentModelDays": 7,
   "recentModelReserveSlots": 5,
   "repositorySizeErrors": {},
-  "repositorySizesComplete": 312,
+  "repositorySizesComplete": 0,
   "skipped": {
-    "fitsKnownCapacity": 1170,
+    "fitsKnownCapacity": 0,
     "gpuCapacityUnknown": 0,
     "repositorySizeUnknown": 0
   },
   "stopErrors": [],
-  "uniqueModels": 312
+  "uniqueModels": 311
 }

.modelhub_state/recent_outcomes.jsonl

@@ -1,3 +1,4 @@
+{"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-patch-tokenizer", "lastSyncTime": "2026-10-07T03:40:15.756923+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "failed", "status": "success", "submitTime": "2026-10-06T09:15:23.045201+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320526", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T19:00:42.266417+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "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_text"], "framework": "vllm", "lastSyncTime": "2026-10-07T00:15:56.875101+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "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_text"], "framework": "vllm", "lastSyncTime": "2026-10-07T00:04:30.851007+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164848+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969016", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164881+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969017", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164891+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969005", "taskType": "text-generation", "verifyResult": null}
-{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164898+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation", "verifyResult": null}

.modelhub_state/recovery_intents.jsonl

@@ -3081,6 +3081,11 @@
 {"batchId": "de9392aa3cad46f08d6c08b0779c8e73", "completedAt": "2026-10-06T23:21:10.024972+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-06T23:21:06.338154+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6a541a5852394d0dad81fb5134482f50", "lastModified": "2026-10-06T18:50:08+00:00", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "reason": null, "reconciledAt": "2026-10-07T03:32:04.522906+00:00", "repoId": "groxaxo/Hemmingway-1-oQ5-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5343725", "taskType": "text-generation"}
 {"batchId": "71c292e2e5bc411881adc1bd35d3ef95", "completedAt": "2026-10-06T23:37:28.428490+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-06T23:37:26.813719+00:00", "framework": "vllm", "intentId": "770e1c9fe5834a99825d448ffad1cc5f", "lastModified": "2026-10-06T18:50:08+00:00", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "reason": null, "reconciledAt": "2026-10-07T03:32:04.524306+00:00", "repoId": "groxaxo/Hemmingway-1-oQ5-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "5343926", "taskType": "text-generation"}
 {"batchId": "474237e700974c388a9adeb7d731b90c", "completedAt": "2026-10-07T00:33:49.626941+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-07T00:32:22.401272+00:00", "framework": "vllm-mlu", "intentId": "14485692bd91476f97f702be29a1ca13", "lastModified": "2026-10-06T18:50:08+00:00", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "reason": null, "reconciledAt": "2026-10-07T03:32:04.525407+00:00", "repoId": "groxaxo/Hemmingway-1-oQ5-MLX", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5344555", "taskType": "text-generation"}
+{"batchId": "ac23136374314f33adccf5ed2675942a", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-07T03:47:02.005916+00:00", "framework": "vllm_tokenizer_patch", "intentId": "29bd3877674f4de9985ba50bfe4a21e1", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
+{"batchId": "ac23136374314f33adccf5ed2675942a", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T03:47:02.006057+00:00", "framework": "vllm", "intentId": "156e924efeec461888741f4522eeb460", "lastModified": "2026-09-28T15:01:07+00:00", "modelAddress": "https://modelscope.cn/models/NovelAI/clio-v1-legacy", "repoId": "NovelAI/clio-v1-legacy", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
+{"batchId": "ac23136374314f33adccf5ed2675942a", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T03:47:02.006118+00:00", "framework": "vllm", "intentId": "6187650f4fdb4986a38caaf2ea5b7658", "lastModified": "2026-09-23T05:44:29+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "repoId": "mlx-community/Hemmingway-1-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
+{"batchId": "ac23136374314f33adccf5ed2675942a", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T03:47:02.006171+00:00", "framework": "vllm", "intentId": "b7eae750b8074d62b5b40a8ba134c60e", "lastModified": "2026-09-22T14:23:22+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
+{"batchId": "ac23136374314f33adccf5ed2675942a", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T03:47:02.006233+00:00", "framework": "vllm", "intentId": "e0a1f4dd77714ae6949792e53e28502a", "lastModified": "2026-09-22T13:08:25+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
 {"batchId": "153072dc168045a58caf7feef74f43a8", "completedAt": "2026-10-06T22:40:43.441060+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-06T21:54:52.534839+00:00", "framework": "vllm", "intentId": "ec9a90f95f8f46a48656c4c390bfb22b", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
 {"batchId": "153072dc168045a58caf7feef74f43a8", "completedAt": "2026-10-06T22:40:43.441057+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-06T21:54:52.534783+00:00", "framework": "vllm", "intentId": "2af91de02d6540dc9930d91a43ba4aaa", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
 {"batchId": "153072dc168045a58caf7feef74f43a8", "completedAt": "2026-10-06T22:40:43.441054+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-06T21:54:52.534726+00:00", "framework": "vllm", "intentId": "856f122a8ddc47d981fa17af35de51c4", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.04.4",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "83c24f100f930a3cb85b193176bf2a7cc0d3ea595fd0cd6f84c60874d6d1b44e",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "e5263c7cf81a80cc509b173baa1bed1af1d08e5e2ecbb374f46963129082d4a0",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "468c8e0ad47fa7a0f8a31ea33dba24f1ffa6c9c6acda604409981cd30ff0ca44",
+    ".modelhub_state/market_intelligence.json": "c810360b81ad085120b29c0fd18b95d7c02f37eacceb023215bc66a75d7ab05b",
-    ".modelhub_state/official_capabilities.json": "e4b85788287068b1912f276a18d8bfba5dd03743bb5cc1ef83896e2373afe44b",
+    ".modelhub_state/official_capabilities.json": "883fcf858e76cc85deddb676405ca246476f6d639ce662abcff79151bf4d6e09",
-    ".modelhub_state/outcome_checkpoint.json": "825cba37de4c460deed7936d1d91190dfa53bd2f02849a73e450c9c341bc91fc",
+    ".modelhub_state/outcome_checkpoint.json": "df692f21ff33adf9871e74e25e8973afecfc8a031ee52a51625471e9051f02ad",
-    ".modelhub_state/queue_cleanup_latest.json": "ac7dfc049da9da5930d3d9f4962bd3c2a0fa628a03049f8e5fa8eca7c87d8fe1",
+    ".modelhub_state/queue_cleanup_latest.json": "d9a4380528da92c12fdaac219608f24ce83d42b748dcf58fed259fa5197fa975",
-    ".modelhub_state/recent_outcomes.jsonl": "a431175c907bbd6eee4fecc9c3aeb926cd1c2b0218bbb9db9c0593e063c02b66",
+    ".modelhub_state/recent_outcomes.jsonl": "69875935f2c41fc67dc3bcb0f3ef13bede5650e0f81d0591aed5cc97b2e66d50",
     ".modelhub_state/recovery_active_tasks.jsonl": "9aca0b4752f40fc34ce800288e56563f7434d1237451717d024cad85db0cba67",
-    ".modelhub_state/recovery_intents.jsonl": "e1f597298647e1d68ba40922e179d7838425508485a9a440eb6259f95dfcef46",
+    ".modelhub_state/recovery_intents.jsonl": "669502848d49888f2a08b6911c0c7e28e79250f36efef2051379391cee8a57ba",
     ".modelhub_state/routing_intelligence.json": "186e379f649ae2f31a690f5030563073799829887e59540698e98641a9ce3b2c",
     ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
     ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
     "ledger/submissions.jsonl": "333cb6768c52e5c8085dd24d6cc4afa8e6ab1c6024db2a6d56f83f4c051bd2f2",
-    "outcomes/submissions.jsonl": "21f4e22d1aac9da5ffd04fbbeb3382474297c5f9597d3e322ce5760c96c1f442"
+    "outcomes/submissions.jsonl": "b46b36a6cdd3f7d2921ca9d552a8941a9a1dab254a4a94b86ce2a9f9fa208dad"
   },
-  "generation": 21686,
+  "generation": 21687,
-  "phase": "cycle",
+  "phase": "intent",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-07T03:39:14.482089+00:00",
+  "updatedAt": "2026-10-07T03:47:02.231108+00:00",
   "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
 }

outcomes/submissions.jsonl

@@ -144,7 +144,6 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671236+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.447710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970349", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901858+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:10:03.058495+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901918+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null}
@@ -794,7 +793,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.348065+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "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": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.351066+00:00", "targetGpu": "Biren_166m", "taskId": "5320014", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347878+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.466690+00:00", "targetGpu": "Biren_166m", "taskId": "5320016", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347700+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "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": 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": "2026-10-06T08:52:27.471074+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320018", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347936+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "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": 16320426072, "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:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.549406+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320020", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T16:58:45.347752+00:00", "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 40884615394, "estimatedRequiredGiB": 45.723, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 40912599808, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20934761652, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "bitsandbytes", "repositoryOnDiskBytes": 40912599808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.748784+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320024", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T16:58:45.348061+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.673292+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320022", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.952783+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "3e142ce0e5532cb370dfb1d96f3aefe603dab6b9b4ad78b11013ad3314b23fa1", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3236010080, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.748451+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320461", "taskType": "text-generation", "verifyResult": null}
@@ -855,15 +853,10 @@
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952222+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 47737939154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "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:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.654477+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320508", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952539+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "03db37da84f8ca79b8ab2a771eab38713ae74b1a74b47d7451ab360bbdb99462", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.659018+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320509", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952762+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.656502+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320510", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952866+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "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": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953094+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "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": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951864+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.872487+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320519", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952323+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.870624+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320516", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951976+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "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": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.868041+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320517", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952216+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.962831+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320524", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952532+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.973292+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320523", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952089+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.955742+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320522", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952652+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-10-06T09:15:23.045201+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320526", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952757+00:00", "modelId": "mlx-community/Mistral-Small-4-119B-2603-OptiQ-2bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45795315925, "estimatedRequiredGiB": 51.2, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 45812947877, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13531266048, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 45812947877}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.964540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320521", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952433+00:00", "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.957174+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320525", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952976+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.961105+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320520", "taskType": "text-generation", "verifyResult": null}
@@ -876,11 +869,9 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952526+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.175204+00:00", "targetGpu": "Biren_166m", "taskId": "5320848", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951965+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.247174+00:00", "targetGpu": "Biren_166m", "taskId": "5320843", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952427+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.167694+00:00", "targetGpu": "Biren_166m", "taskId": "5320845", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952318+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "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": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.155386+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320840", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953072+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.246121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320837", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952971+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.169263+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320838", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952084+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.164156+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320847", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951857+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.158538+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320844", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952751+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.173573+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320846", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952966+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.269594+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320851", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952312+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.258284+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320850", "taskType": "text-generation", "verifyResult": null}
@@ -889,10 +880,7 @@
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952520+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.328612+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320853", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952422+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "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": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.264608+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320855", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952203+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.272338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320856", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952746+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "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": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.273637+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320854", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953067+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.363114+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320859", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951958+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "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": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.374943+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320857", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952849+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "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": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.361277+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320858", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952640+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.359681+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320860", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952307+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.463228+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320862", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951842+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.477950+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320861", "taskType": "text-generation", "verifyResult": null}
@@ -919,8 +907,6 @@
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953057+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.253231+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320883", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951946+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.272792+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320884", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952296+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "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": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.275101+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320885", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952061+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "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": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951827+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "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": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "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:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952174+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "1808282a6a7e87463f4fe68a059e74642ad7fba49ec04a246f0c3ea29ccfa12b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.372146+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320887", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952952+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.367923+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320889", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952405+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.366014+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320893", "taskType": "text-generation", "verifyResult": null}
@@ -1072,7 +1058,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:46:15.564156+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343299", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:46:15.745022+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343306", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T23:00:25.957994+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343527", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T23:17:07.153265+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5343702", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T23:21:09.752397+00:00", "targetGpu": "Biren_166m", "taskId": "5343725", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T23:37:28.160203+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5343926", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T00:32:27.150657+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5344555", "taskType": "text-generation", "verifyResult": null}