state: generation 22215 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -965,6 +965,27 @@
       "targetGpu": "Cambricon_mlu-370-x8",
       "taskType": "text-generation"
     },
+    "cambricon_mlu-370-x8|vllm-mlu|text-generation|architectures:sseswamobaforcausallm": {
+      "architectureSignature": "architectures:sseswamobaforcausallm",
+      "architectures": [
+        "sseswamobaforcausallm"
+      ],
+      "evidenceCount": 1,
+      "expiresAt": "2026-10-22T05:48:17.265295+00:00",
+      "framework": "vllm-mlu",
+      "latestFailureAt": "2026-09-22T05:48:17.265295+00:00",
+      "latestSuccessfulAt": null,
+      "matchType": "architectures",
+      "modelType": null,
+      "sourceModelIds": [
+        "Panyuqi/SpikingBrain-2.0-base-8k"
+      ],
+      "sourceTaskIds": [
+        "5013248"
+      ],
+      "targetGpu": "Cambricon_mlu-370-x8",
+      "taskType": "text-generation"
+    },
     "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
       "architectureSignature": "model_type:mini_k3",
       "architectures": [],
@@ -1367,25 +1388,6 @@
       "targetGpu": "hygon_k100-ai",
       "taskType": "text-generation"
     },
-    "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:zaya": {
-      "architectureSignature": "model_type:zaya",
-      "architectures": [],
-      "evidenceCount": 1,
-      "expiresAt": "2026-10-08T14:03:45.031522+00:00",
-      "framework": "vllm-patch-tokenizer",
-      "latestFailureAt": "2026-09-08T14:03:45.031522+00:00",
-      "latestSuccessfulAt": null,
-      "matchType": "model_type",
-      "modelType": "zaya",
-      "sourceModelIds": [
-        "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M"
-      ],
-      "sourceTaskIds": [
-        "4720262"
-      ],
-      "targetGpu": "hygon_k100-ai",
-      "taskType": "text-generation"
-    },
     "hygon_k100-ai|vllm|text-generation|architectures:spark2_5forcausallm": {
       "architectureSignature": "architectures:spark2_5forcausallm",
       "architectures": [
@@ -2889,7 +2891,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-08T13:56:53.164282+00:00",
+  "generatedAt": "2026-10-08T14:08:43.756860+00:00",
   "summary": {
     "activeBlockCount": 144,
     "byGpuFramework": {
@@ -2903,7 +2905,7 @@
       "Cambricon_mlu-370-x4|vllm-mlu": 1,
       "Cambricon_mlu-370-x8|vllm": 14,
       "Cambricon_mlu-370-x8|vllm-customized": 6,
-      "Cambricon_mlu-370-x8|vllm-mlu": 2,
+      "Cambricon_mlu-370-x8|vllm-mlu": 3,
       "Iluvatar_bi-150|transformers": 5,
       "Iluvatar_bi-150|vllm": 6,
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 4,
@@ -2919,7 +2921,7 @@
       "Vastai_va16|vllm": 7,
       "Vastai_va16|vllm_fix_tokenizer": 3,
       "hygon_k100-ai|vllm": 8,
-      "hygon_k100-ai|vllm-patch-tokenizer": 5
+      "hygon_k100-ai|vllm-patch-tokenizer": 4
     },
     "ttlDays": 30
   }

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-08T14:06:26.155317+00:00",
+  "generatedAt": "2026-10-08T14:10:09.958068+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-08T13:49:20.816400+00:00",
+  "generatedAt": "2026-10-08T14:08:43.644540+00:00",
-  "lastSyncTime": "2026-10-08T13:49:20.758865+00:00",
+  "lastSyncTime": "2026-10-08T14:08:43.365639+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -969,6 +969,27 @@
         "targetGpu": "Cambricon_mlu-370-x8",
         "taskType": "text-generation"
       },
+      "cambricon_mlu-370-x8|vllm-mlu|text-generation|architectures:sseswamobaforcausallm": {
+        "architectureSignature": "architectures:sseswamobaforcausallm",
+        "architectures": [
+          "sseswamobaforcausallm"
+        ],
+        "evidenceCount": 1,
+        "expiresAt": "2026-10-22T05:48:17.265295+00:00",
+        "framework": "vllm-mlu",
+        "latestFailureAt": "2026-09-22T05:48:17.265295+00:00",
+        "latestSuccessfulAt": null,
+        "matchType": "architectures",
+        "modelType": null,
+        "sourceModelIds": [
+          "Panyuqi/SpikingBrain-2.0-base-8k"
+        ],
+        "sourceTaskIds": [
+          "5013248"
+        ],
+        "targetGpu": "Cambricon_mlu-370-x8",
+        "taskType": "text-generation"
+      },
       "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
         "architectureSignature": "model_type:mini_k3",
         "architectures": [],
@@ -1371,25 +1392,6 @@
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation"
       },
-      "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:zaya": {
-        "architectureSignature": "model_type:zaya",
-        "architectures": [],
-        "evidenceCount": 1,
-        "expiresAt": "2026-10-08T14:03:45.031522+00:00",
-        "framework": "vllm-patch-tokenizer",
-        "latestFailureAt": "2026-09-08T14:03:45.031522+00:00",
-        "latestSuccessfulAt": null,
-        "matchType": "model_type",
-        "modelType": "zaya",
-        "sourceModelIds": [
-          "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M"
-        ],
-        "sourceTaskIds": [
-          "4720262"
-        ],
-        "targetGpu": "hygon_k100-ai",
-        "taskType": "text-generation"
-      },
       "hygon_k100-ai|vllm|text-generation|architectures:spark2_5forcausallm": {
         "architectureSignature": "architectures:spark2_5forcausallm",
         "architectures": [
@@ -2906,7 +2908,7 @@
         "Cambricon_mlu-370-x4|vllm-mlu": 1,
         "Cambricon_mlu-370-x8|vllm": 14,
         "Cambricon_mlu-370-x8|vllm-customized": 6,
-        "Cambricon_mlu-370-x8|vllm-mlu": 2,
+        "Cambricon_mlu-370-x8|vllm-mlu": 3,
         "Iluvatar_bi-150|transformers": 5,
         "Iluvatar_bi-150|vllm": 6,
         "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 4,
@@ -2922,7 +2924,7 @@
         "Vastai_va16|vllm": 7,
         "Vastai_va16|vllm_fix_tokenizer": 3,
         "hygon_k100-ai|vllm": 8,
-        "hygon_k100-ai|vllm-patch-tokenizer": 5
+        "hygon_k100-ai|vllm-patch-tokenizer": 4
       },
       "ttlDays": 30
     },
@@ -3598,28 +3600,28 @@
         "unresolvedFailureCount": 47
       },
       "Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
-        "attributableFailureCount": 24,
+        "attributableFailureCount": 25,
-        "decisionFailureRate": 0.6486,
+        "decisionFailureRate": 0.6579,
-        "decisionSuccessRate": 0.3514,
+        "decisionSuccessRate": 0.3421,
-        "decisionTotal": 37,
+        "decisionTotal": 38,
         "failureBreakdown": {
           "ambiguous_runtime": 54,
-          "framework_architecture_unsupported": 20,
+          "framework_architecture_unsupported": 21,
           "model_load": 3,
           "tokenizer_compatibility": 1,
           "参数/模板问题": 40
         },
-        "failureCount": 118,
+        "failureCount": 119,
-        "failureRate": 0.9008,
+        "failureRate": 0.9015,
         "framework": "vllm-mlu",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 13,
-        "successRate": 0.0992,
+        "successRate": 0.0985,
         "targetGpu": "Cambricon_mlu-370-x8",
         "taskType": "text-generation",
-        "total": 131,
+        "total": 132,
         "unresolvedFailureCount": 94
       },
       "Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -5673,27 +5675,27 @@
         "unresolvedFailureCount": 51
       },
       "vllm-mlu": {
-        "attributableFailureCount": 54,
+        "attributableFailureCount": 55,
-        "decisionFailureRate": 0.7105,
+        "decisionFailureRate": 0.7143,
-        "decisionSuccessRate": 0.2895,
+        "decisionSuccessRate": 0.2857,
-        "decisionTotal": 76,
+        "decisionTotal": 77,
         "failureBreakdown": {
           "ambiguous_runtime": 103,
-          "framework_architecture_unsupported": 46,
+          "framework_architecture_unsupported": 47,
           "model_load": 7,
           "platform_infrastructure": 1,
           "tokenizer_compatibility": 1,
           "参数/模板问题": 42,
           "验证失败": 3
         },
-        "failureCount": 203,
+        "failureCount": 204,
-        "failureRate": 0.9022,
+        "failureRate": 0.9027,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 22,
-        "successRate": 0.0978,
+        "successRate": 0.0973,
-        "total": 225,
+        "total": 226,
         "unresolvedFailureCount": 148
       },
       "vllm-patch-tokenizer": {
@@ -5797,7 +5799,7 @@
         "unresolvedFailureCount": 304
       }
     },
-    "generatedAt": "2026-10-08T13:49:20.802999+00:00",
+    "generatedAt": "2026-10-08T14:08:43.631230+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 124,
@@ -5914,13 +5916,13 @@
         "unresolvedFailureCount": 874
       },
       "Cambricon_mlu-370-x8": {
-        "attributableFailureCount": 70,
+        "attributableFailureCount": 71,
-        "decisionFailureRate": 0.8235,
+        "decisionFailureRate": 0.8256,
-        "decisionSuccessRate": 0.1765,
+        "decisionSuccessRate": 0.1744,
-        "decisionTotal": 85,
+        "decisionTotal": 86,
         "failureBreakdown": {
           "ambiguous_runtime": 158,
-          "framework_architecture_unsupported": 57,
+          "framework_architecture_unsupported": 58,
           "memory_capacity": 4,
           "model_load": 6,
           "platform_infrastructure": 2,
@@ -5928,14 +5930,14 @@
           "参数/模板问题": 78,
           "验证失败": 22
         },
-        "failureCount": 330,
+        "failureCount": 331,
-        "failureRate": 0.9565,
+        "failureRate": 0.9566,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 2,
         "successCount": 15,
-        "successRate": 0.0435,
+        "successRate": 0.0434,
-        "total": 345,
+        "total": 346,
         "unresolvedFailureCount": 258
       },
       "Iluvatar_bi-100": {
@@ -14109,6 +14111,29 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sse_swa_moba|none": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm-mlu",
+        "modelType": "sse_swa_moba",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x8",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -26865,6 +26890,31 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sse_swa_moba|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-mlu",
+        "lastTerminalAt": "2026-10-08T14:08:43.365639+00:00",
+        "modelType": "sse_swa_moba",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x8",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none": {
         "attributableFailureCount": 6,
         "consecutiveFailures": 6,
@@ -39778,6 +39828,30 @@
         "total": 1,
         "unresolvedFailureCount": 1
       },
+      "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sse_swa_moba|none|33": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm-mlu",
+        "loadSizeLog2Bucket": 33,
+        "modelType": "sse_swa_moba",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Cambricon_mlu-370-x8",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|31": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -57198,20 +57272,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17703,
+    "terminalRecords": 17704,
-    "totalRecords": 18190,
+    "totalRecords": 18191,
     "totals": {
-      "attributableFailureCount": 6296,
+      "attributableFailureCount": 6297,
       "decisionFailureRate": 0.8654,
       "decisionSuccessRate": 0.1346,
-      "decisionTotal": 7275,
+      "decisionTotal": 7276,
       "failureBreakdown": {
         "ambiguous_runtime": 4599,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 130,
         "context_length": 327,
-        "framework_architecture_unsupported": 2314,
+        "framework_architecture_unsupported": 2315,
         "memory_capacity": 1206,
         "model_load": 571,
         "platform_infrastructure": 955,
@@ -57222,14 +57296,14 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16724,
+      "failureCount": 16725,
       "failureRate": 0.9447,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 955,
       "successCount": 979,
       "successRate": 0.0553,
-      "total": 17703,
+      "total": 17704,
       "unresolvedFailureCount": 9473
     },
     "warnings": [
@@ -57239,13 +57313,13 @@
       "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57292,6 +57366,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 18190,
+  "summarizedRecords": 18191,
   "version": 1
 }

.modelhub_state/queue_cleanup_latest.json

@@ -14,13 +14,13 @@
     100
   ],
   "accounts": 12,
-  "activeScanned": 1009,
+  "activeScanned": 1013,
   "ageCleanupMode": "admission_only",
   "agePolicySkipped": {
     "cleanupDisabled": true,
     "reason": "admission_only"
   },
-  "architectureBlockCount": 145,
+  "architectureBlockCount": 144,
   "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",
@@ -61,32 +46,15 @@
       "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": {},
@@ -114,12 +82,12 @@
     "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": 163,
-    "noMatchingBlock": 830,
+    "noMatchingBlock": 834,
     "partiallyBlockedFrameworkSet": 16,
     "runningMatchedProtected": 0,
     "submissionContextMismatch": 0,
@@ -160,12 +128,12 @@
   "recentModelDays": 7,
   "recentModelReserveSlots": 5,
   "repositorySizeErrors": {},
-  "repositorySizesComplete": 307,
+  "repositorySizesComplete": 0,
   "skipped": {
-    "fitsKnownCapacity": 1009,
+    "fitsKnownCapacity": 0,
     "gpuCapacityUnknown": 0,
     "repositorySizeUnknown": 0
   },
   "stopErrors": [],
-  "uniqueModels": 307
+  "uniqueModels": 312
 }

.modelhub_state/recent_outcomes.jsonl

@@ -243,6 +243,7 @@
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T11:35:31.353790+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "failed", "status": "success", "submitTime": "2026-09-22T06:15:24.089191+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013573", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557099+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.552227+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013340", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557020+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.550868+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013339", "taskType": "text-generation", "verifyResult": null}
+{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["SSESWAMoBAForCausalLM"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T14:08:43.365639+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "failed", "status": "success", "submitTime": "2026-09-22T05:48:17.265295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5013248", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557144+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:36:08.409002+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013035", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557127+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:29:49.361193+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5012953", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-customized", "lastSyncTime": "2026-09-29T17:54:53.270719+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "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:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.098010+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012909", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383779+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T22:38:57.960315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008253", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T18:18:51.743129+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "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": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:21:59.843515+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5008078", "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": ["mini_k3"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T20:23:14.668330+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "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": null, "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": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:14:33.594032+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008009", "taskType": "text-generation", "verifyResult": -1}
-{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383864+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T22:14:33.592720+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008010", "taskType": "text-generation", "verifyResult": null}

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.22.1",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "f87b5fbb3377a82b53bab990b77e58082c25483b6b4b4c8ba926735793ace4e7",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "4e272070103f03ff68e246d5a598acfd72655056f7b04b9cb258ab762c134a14",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "df8a0e8697b54576656b17940b514acdfeb91cf2fe13958bced06daa0877e341",
+    ".modelhub_state/market_intelligence.json": "74b89d38ebaaece6aee9484fc13b34e0b62475ed93f078f1c7ae15333ba50f45",
-    ".modelhub_state/official_capabilities.json": "efb40c300e5a9b87bb8568f90c7efdbeeadda4b1dc73e52fed2d76f80925f317",
+    ".modelhub_state/official_capabilities.json": "fd409700f742cbd8181a158a0d366b6fd6751adf764cf08369eb56dc75672c42",
-    ".modelhub_state/outcome_checkpoint.json": "d717c251dd9274caa21381002b59615db2ca814f5989f2b3bc3fa5898036d59a",
+    ".modelhub_state/outcome_checkpoint.json": "00bb3e1976c0b7d61ded767f7553bdabed2a55a92a6bf7cc077833912573d2cc",
-    ".modelhub_state/queue_cleanup_latest.json": "9a0567db027598f84427b0a7f62c7d9ca2584466d0e5f57d44dba9aeaca87c4f",
+    ".modelhub_state/queue_cleanup_latest.json": "c008ccfd482c606b5c4db49fdfd5361b929a8d5f09745153cb398fdcd797482d",
-    ".modelhub_state/recent_outcomes.jsonl": "8e2bfbc6eb05777878481e2e185be47c7067269e8595a45e85bdff066f61ae88",
+    ".modelhub_state/recent_outcomes.jsonl": "6b6110b4e36d568071f216d853646b7193918ed0871427055f9c218e76202d47",
-    ".modelhub_state/recovery_active_tasks.jsonl": "9e760dc971b70500d089e82ca2e8f9bb349fbbb6d69727d815369ad76ba24cd9",
+    ".modelhub_state/recovery_active_tasks.jsonl": "d207cf79218117069c15ace816c3ac38a666916caf5772e80193b086ac38b38a",
-    ".modelhub_state/recovery_intents.jsonl": "5057de6e50e453d534409716d961dec691509bcb49cbde92fd0de6a6bc338e62",
+    ".modelhub_state/recovery_intents.jsonl": "94ae65d034de5c948f45d64dd90a81f71e20a7ac1bf96dc716c0561d6225458c",
     ".modelhub_state/routing_intelligence.json": "13b864597fc4d26de7806bc18cb3cf6cbcf18c0eaac4bfe9460a9932a48cb392",
     ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
     ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
     "ledger/submissions.jsonl": "526b97a2b1100e6304ee65252c90860fc2391aa589c1782bf7ce0b2e80c364ec",
-    "outcomes/submissions.jsonl": "520cfb5207715f9948d6edf3c93a20c1f93399a8c12adaa5777538059d3db9c6"
+    "outcomes/submissions.jsonl": "80a09cb95a890325406a2845ee23748f6f0274ee305637aaa7d4ca18f39a86ec"
   },
-  "generation": 22214,
+  "generation": 22215,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-08T14:08:40.129048+00:00",
+  "updatedAt": "2026-10-08T14:10:38.734174+00:00",
   "writerId": "dc0ce4714e0442da8f6b0a08a8a7cb03"
 }

outcomes/submissions.jsonl

@@ -226,7 +226,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T13:37:53.563477+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034915504, "estimatedRequiredGiB": 2.278, "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": null, "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": 2038530279}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:34:46.454174+00:00", "targetGpu": "Biren_166m", "taskId": "5013017", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T13:46:14.276964+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:42:55.602315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5013164", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T13:46:14.277018+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "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": null, "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": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:45:37.003989+00:00", "targetGpu": "Biren_166m", "taskId": "5013207", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T13:49:59.752651+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-22T05:48:17.265295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5013248", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T13:53:56.878088+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "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": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "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": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:52:13.652441+00:00", "targetGpu": "Biren_166m", "taskId": "5013306", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T13:58:31.356521+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": null, "modelscopeLicense": "mit", "modelscopeParams": null, "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": "2026-09-22T05:55:01.182755+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5013341", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:58:31.356490+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:58:14.744160+00:00", "targetGpu": "MetaX_c-500", "taskId": "5013402", "taskType": "text-generation", "verifyResult": null}
@@ -864,7 +863,7 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T12:56:53.956707+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T04:54:20.845170+00:00", "targetGpu": "Biren_166m", "taskId": "5369290", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T13:32:52.563309+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T05:16:49.666742+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5370509", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T13:40:06.048902+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T05:37:38.062655+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5370970", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-08T05:58:20.455529+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5371644", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T14:08:43.365608+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T05:58:20.455529+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5371644", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-08T06:31:25.488466+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5372502", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-08T07:35:16.860851+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5373903", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ConwayResearch/woof-1.0-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3034300817, "estimatedRequiredGiB": 3.421, "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": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:underdog", "custom_tag:browser-agent", "custom_tag:on-device"], "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": "2026-10-07T11:42:31.164621+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": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 3061126882}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-08T07:53:26.754879+00:00", "targetGpu": "Biren_166m", "taskId": "5374322", "taskType": "text-generation", "verifyResult": null}