state: generation 21389 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -2815,7 +2815,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-10-06T09:47:55.256039+00:00",
+  "generatedAt": "2026-10-06T10:16:23.066559+00:00",
   "summary": {
     "activeBlockCount": 142,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-10-06T10:11:20.847113+00:00",
+  "generatedAt": "2026-10-06T10:16:23.142341+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-10-06T10:11:20.847113+00:00",
+  "catalogUpdatedAt": "2026-10-06T10:16:23.142341+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-10-06T10:14:55.889012+00:00",
+  "generatedAt": "2026-10-06T10:16:23.142341+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6553,6 +6553,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-10-06T10:11:20.847113+00:00",
+  "taskTreeUpdatedAt": "2026-10-06T10:16:23.142341+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-10-06T09:15:34.201863+00:00",
+  "generatedAt": "2026-10-06T10:16:22.973460+00:00",
-  "lastSyncTime": "2026-10-06T09:15:33.969896+00:00",
+  "lastSyncTime": "2026-10-06T10:16:22.659565+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3525,24 +3525,24 @@
         "decisionSuccessRate": 0.4194,
         "decisionTotal": 31,
         "failureBreakdown": {
-          "ambiguous_runtime": 53,
+          "ambiguous_runtime": 54,
           "framework_architecture_unsupported": 14,
           "model_load": 3,
           "tokenizer_compatibility": 1,
           "参数/模板问题": 3
         },
-        "failureCount": 74,
+        "failureCount": 75,
-        "failureRate": 0.8506,
+        "failureRate": 0.8523,
         "framework": "vllm-mlu",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 13,
-        "successRate": 0.1494,
+        "successRate": 0.1477,
         "targetGpu": "Cambricon_mlu-370-x8",
         "taskType": "text-generation",
-        "total": 87,
+        "total": 88,
-        "unresolvedFailureCount": 56
+        "unresolvedFailureCount": 57
       },
       "Cambricon_mlu-370-x8|vllm|text-generation": {
         "attributableFailureCount": 22,
@@ -5151,27 +5151,27 @@
         "unresolvedFailureCount": 3
       },
       "Vastai_va16|vllm_fix_tokenizer|text-generation": {
-        "attributableFailureCount": 35,
+        "attributableFailureCount": 36,
-        "decisionFailureRate": 0.875,
+        "decisionFailureRate": 0.878,
-        "decisionSuccessRate": 0.125,
+        "decisionSuccessRate": 0.122,
-        "decisionTotal": 40,
+        "decisionTotal": 41,
         "failureBreakdown": {
           "ambiguous_runtime": 26,
-          "framework_architecture_unsupported": 23,
+          "framework_architecture_unsupported": 24,
           "model_load": 12,
           "参数/模板问题": 4
         },
-        "failureCount": 65,
+        "failureCount": 66,
-        "failureRate": 0.9286,
+        "failureRate": 0.9296,
         "framework": "vllm_fix_tokenizer",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 5,
-        "successRate": 0.0714,
+        "successRate": 0.0704,
         "targetGpu": "Vastai_va16",
         "taskType": "text-generation",
-        "total": 70,
+        "total": 71,
         "unresolvedFailureCount": 30
       },
       "Vastai_va16|vllm|text-generation": {
@@ -5575,7 +5575,7 @@
         "decisionSuccessRate": 0.3333,
         "decisionTotal": 66,
         "failureBreakdown": {
-          "ambiguous_runtime": 101,
+          "ambiguous_runtime": 102,
           "framework_architecture_unsupported": 36,
           "model_load": 7,
           "platform_infrastructure": 1,
@@ -5583,15 +5583,15 @@
           "参数/模板问题": 4,
           "验证失败": 3
         },
-        "failureCount": 153,
+        "failureCount": 154,
-        "failureRate": 0.8743,
+        "failureRate": 0.875,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 1,
         "successCount": 22,
-        "successRate": 0.1257,
+        "successRate": 0.125,
-        "total": 175,
+        "total": 176,
-        "unresolvedFailureCount": 108
+        "unresolvedFailureCount": 109
       },
       "vllm-patch-tokenizer": {
         "attributableFailureCount": 61,
@@ -5641,28 +5641,28 @@
         "unresolvedFailureCount": 34
       },
       "vllm_fix_tokenizer": {
-        "attributableFailureCount": 171,
+        "attributableFailureCount": 172,
-        "decisionFailureRate": 0.9716,
+        "decisionFailureRate": 0.9718,
-        "decisionSuccessRate": 0.0284,
+        "decisionSuccessRate": 0.0282,
-        "decisionTotal": 176,
+        "decisionTotal": 177,
         "failureBreakdown": {
           "ambiguous_runtime": 355,
           "backend_operator": 9,
-          "framework_architecture_unsupported": 46,
+          "framework_architecture_unsupported": 47,
           "memory_capacity": 10,
           "model_load": 12,
           "platform_infrastructure": 25,
           "tokenizer_compatibility": 94,
           "参数/模板问题": 13
         },
-        "failureCount": 564,
+        "failureCount": 565,
         "failureRate": 0.9912,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 25,
         "successCount": 5,
         "successRate": 0.0088,
-        "total": 569,
+        "total": 570,
         "unresolvedFailureCount": 368
       },
       "vllm_tokenizer_patch": {
@@ -5694,7 +5694,7 @@
         "unresolvedFailureCount": 233
       }
     },
-    "generatedAt": "2026-10-06T09:15:34.186944+00:00",
+    "generatedAt": "2026-10-06T10:16:22.954602+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 119,
@@ -5816,7 +5816,7 @@
         "decisionSuccessRate": 0.1899,
         "decisionTotal": 79,
         "failureBreakdown": {
-          "ambiguous_runtime": 157,
+          "ambiguous_runtime": 158,
           "framework_architecture_unsupported": 51,
           "memory_capacity": 4,
           "model_load": 6,
@@ -5825,15 +5825,15 @@
           "参数/模板问题": 41,
           "验证失败": 22
         },
-        "failureCount": 286,
+        "failureCount": 287,
-        "failureRate": 0.9502,
+        "failureRate": 0.9503,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 2,
         "successCount": 15,
-        "successRate": 0.0498,
+        "successRate": 0.0497,
-        "total": 301,
+        "total": 302,
-        "unresolvedFailureCount": 220
+        "unresolvedFailureCount": 221
       },
       "Iluvatar_bi-100": {
         "attributableFailureCount": 194,
@@ -6059,14 +6059,14 @@
         "unresolvedFailureCount": 422
       },
       "Vastai_va16": {
-        "attributableFailureCount": 467,
+        "attributableFailureCount": 468,
-        "decisionFailureRate": 0.8912,
+        "decisionFailureRate": 0.8914,
-        "decisionSuccessRate": 0.1088,
+        "decisionSuccessRate": 0.1086,
-        "decisionTotal": 524,
+        "decisionTotal": 525,
         "failureBreakdown": {
           "ambiguous_runtime": 826,
           "context_length": 9,
-          "framework_architecture_unsupported": 202,
+          "framework_architecture_unsupported": 203,
           "memory_capacity": 133,
           "model_load": 54,
           "platform_infrastructure": 14,
@@ -6076,14 +6076,14 @@
           "日志缺失": 124,
           "验证失败": 130
         },
-        "failureCount": 1803,
+        "failureCount": 1804,
         "failureRate": 0.9694,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 14,
         "successCount": 57,
         "successRate": 0.0306,
-        "total": 1860,
+        "total": 1861,
         "unresolvedFailureCount": 1322
       },
       "hygon_k100-ai": {
@@ -13113,9 +13113,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 2
+          "ambiguous_runtime": 3
         },
-        "failureCount": 2,
+        "failureCount": 3,
         "failureRate": 1.0,
         "framework": "vllm-mlu",
         "modelType": "lfm2",
@@ -13127,8 +13127,8 @@
         "successRate": 0.0,
         "targetGpu": "Cambricon_mlu-370-x8",
         "taskType": "text-generation",
-        "total": 2,
+        "total": 3,
-        "unresolvedFailureCount": 2
+        "unresolvedFailureCount": 3
       },
       "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq": {
         "attributableFailureCount": 0,
@@ -23337,14 +23337,14 @@
         "unresolvedFailureCount": 0
       },
       "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none": {
-        "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_fix_tokenizer",
         "modelType": "spark2_5",
@@ -23356,7 +23356,7 @@
         "successRate": 0.0,
         "targetGpu": "Vastai_va16",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
         "unresolvedFailureCount": 0
       },
       "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|torchao": {
@@ -39955,6 +39955,30 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none|30": {
+        "attributableFailureCount": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm-mlu",
+        "loadSizeLog2Bucket": 30,
+        "modelType": "lfm2",
+        "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": 1
+      },
       "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|30": {
         "attributableFailureCount": 0,
         "decisionFailureRate": 0.0,
@@ -55178,6 +55202,30 @@
         "total": 1,
         "unresolvedFailureCount": 0
       },
+      "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none|31": {
+        "attributableFailureCount": 1,
+        "decisionFailureRate": 1.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 1,
+        "failureBreakdown": {
+          "framework_architecture_unsupported": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm_fix_tokenizer",
+        "loadSizeLog2Bucket": 31,
+        "modelType": "spark2_5",
+        "pendingCount": 0,
+        "pendingRate": 0.0,
+        "platformFailureCount": 0,
+        "quantizationMethod": "none",
+        "successCount": 0,
+        "successRate": 0.0,
+        "targetGpu": "Vastai_va16",
+        "taskType": "text-generation",
+        "total": 1,
+        "unresolvedFailureCount": 0
+      },
       "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none|32": {
         "attributableFailureCount": 1,
         "decisionFailureRate": 1.0,
@@ -57345,20 +57393,20 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17331,
+    "terminalRecords": 17333,
-    "totalRecords": 17555,
+    "totalRecords": 17557,
     "totals": {
-      "attributableFailureCount": 6231,
+      "attributableFailureCount": 6232,
-      "decisionFailureRate": 0.8643,
+      "decisionFailureRate": 0.8644,
-      "decisionSuccessRate": 0.1357,
+      "decisionSuccessRate": 0.1356,
-      "decisionTotal": 7209,
+      "decisionTotal": 7210,
       "failureBreakdown": {
-        "ambiguous_runtime": 4543,
+        "ambiguous_runtime": 4544,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 129,
         "context_length": 327,
-        "framework_architecture_unsupported": 2257,
+        "framework_architecture_unsupported": 2258,
         "memory_capacity": 1206,
         "model_load": 566,
         "platform_infrastructure": 951,
@@ -57369,15 +57417,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16353,
+      "failureCount": 16355,
       "failureRate": 0.9436,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 951,
       "successCount": 978,
       "successRate": 0.0564,
-      "total": 17331,
+      "total": 17333,
-      "unresolvedFailureCount": 9171
+      "unresolvedFailureCount": 9172
     },
     "warnings": [
       "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -57386,14 +57434,14 @@
       "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 Ascend_910-b3 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
       "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
-      "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
+      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
       "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57437,6 +57485,6 @@
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17555,
+  "summarizedRecords": 17557,
   "version": 1
 }

manifest.json

@@ -2,24 +2,24 @@
   "agentVersion": "2026.09.04.4",
   "checksums": {
     ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
-    ".modelhub_state/architecture_compatibility_blacklist.json": "51b26b0425e9560247ef612a9bd44cdcc344c20ba8e5a29ab5bd87e30d4ee020",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "f2b92d0f796d9843ebf5147b0c0937086e1b41096d82929b7541788560c4feb0",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "6166a986cd8139412ba7a7bff22422ff557e0ac38bec481cad33c8a18a75466c",
+    ".modelhub_state/market_intelligence.json": "edfa4dd7670825a72dc51776577443d2d99a2de2aa5ed14fc6f775ec856a4175",
-    ".modelhub_state/official_capabilities.json": "c24a0ee67df629a26c917ece9c4dee8d125234c6c8af557dc0d10cc1cf877c1f",
+    ".modelhub_state/official_capabilities.json": "e635835854794327fb704768dbf9d7d5872842fdf8976d02f28c960cf61aaa36",
-    ".modelhub_state/outcome_checkpoint.json": "e468433c8bf35e1c604059533798b694e68c885ac9e9b21ee4e7f5ad2be76c86",
+    ".modelhub_state/outcome_checkpoint.json": "e6d8888b76a870a301d871a94565ba31756178e8cb535daf9f7b845ec177deca",
     ".modelhub_state/queue_cleanup_latest.json": "5a0303e8316fcab30a4e922547230f80795528b823c5599adce914d800fab218",
     ".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac",
-    ".modelhub_state/recovery_active_tasks.jsonl": "9b823c4f62799a911df7d5579fa937655d1596395fbf1c6561233d568a0d9a60",
+    ".modelhub_state/recovery_active_tasks.jsonl": "1f75e24f908a6b13716793e4fe3c683d087a906b8c0e4fc97da9ee9c88de577e",
-    ".modelhub_state/recovery_intents.jsonl": "453f5948ae359d39758b221b6fb49c566b3ad36f3f6ca80a83e77b82ac1155c6",
+    ".modelhub_state/recovery_intents.jsonl": "33e2b7d71a311302fab93aee49bf51d7fe4619d49327a3b6cd1fc327f4a5e435",
     ".modelhub_state/routing_intelligence.json": "135d2bcf793437776a45fc73fe9554e7090843ec9af2869275661344f09230da",
     ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
     ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
     "ledger/submissions.jsonl": "ecca1775f01f23b4ea1a5d7090c4995bbeb88a2004eb3b1cfa85ed5436818500",
-    "outcomes/submissions.jsonl": "0350c3d9e7a36cd54253ef04faf29ec5be0a7db998e0d930b40539111680f297"
+    "outcomes/submissions.jsonl": "287ef30b44290594ac8ce81591beb2e76def28800e0f69d62cf6ede65ba84265"
   },
-  "generation": 21388,
+  "generation": 21389,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-06T10:16:19.089823+00:00",
+  "updatedAt": "2026-10-06T10:16:29.049186+00:00",
   "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
 }

outcomes/submissions.jsonl

@@ -138,7 +138,6 @@
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063090+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "87e2d06ee2cbb5d6c759a240df54c78746d706859f9a364e78515c8f28fcc1fd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.174402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947147", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063052+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "a0e7803b6725f735d0804da4c3b2af6ac5c0db91adef3494b64f29a43c4cded8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.177348+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947146", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063105+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "ed217196ebf72901791ffd67a7627878fd8f0fd29fa1291cafd8f6b32c01507f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.175900+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947142", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T01:58:16.407602+00:00", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "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": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_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:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T17:49:27.865419+00:00", "targetGpu": "Vastai_va16", "taskId": "4961188", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647557+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.040710+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969021", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null}
@@ -162,7 +161,6 @@
 {"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}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:34:29.856278+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:29:38.381652+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970762", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T16:51:24.761939+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-20T08:49:13.744928+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974217", "taskType": "text-generation", "verifyResult": null}