state: generation 18672 (cycle)

.modelhub_state/architecture_compatibility_blacklist.json

@@ -3299,7 +3299,7 @@
       "taskType": "text-generation"
     }
   },
-  "generatedAt": "2026-09-30T04:52:05.648404+00:00",
+  "generatedAt": "2026-09-30T05:01:54.574498+00:00",
   "summary": {
     "activeBlockCount": 166,
     "byGpuFramework": {

.modelhub_state/market_intelligence.json

@@ -1,8 +1,8 @@
 {
-  "communityAttemptedAt": "2026-09-30T04:48:07.351373+00:00",
+  "communityAttemptedAt": "2026-09-30T05:03:35.758691+00:00",
   "communityError": null,
   "communitySample": {},
-  "communityUpdatedAt": "2026-09-30T04:48:07.351373+00:00",
+  "communityUpdatedAt": "2026-09-30T05:03:35.758691+00:00",
   "frameworkAttemptedAt": "2026-09-30T02:21:12.566642+00:00",
   "frameworkError": null,
   "frameworkStats": {
@@ -434,7 +434,7 @@
     }
   },
   "frameworkUpdatedAt": null,
-  "generatedAt": "2026-09-30T05:00:09.166600+00:00",
+  "generatedAt": "2026-09-30T05:03:35.758691+00:00",
   "gpuStats": {
     "Ascend_910-b3": {
       "available": true,

.modelhub_state/official_capabilities.json

@@ -1,5 +1,5 @@
 {
-  "catalogUpdatedAt": "2026-09-30T05:00:09.166600+00:00",
+  "catalogUpdatedAt": "2026-09-30T05:03:35.758691+00:00",
   "configuredTaskTypes": [
     "text-generation"
   ],
@@ -56,7 +56,7 @@
     "time-series-forecasting"
   ],
   "errors": [],
-  "generatedAt": "2026-09-30T05:00:09.166600+00:00",
+  "generatedAt": "2026-09-30T05:03:35.758691+00:00",
   "gpuCatalog": {
     "Ascend_910-b3": {
       "canVerify": true,
@@ -6337,6 +6337,6 @@
       "updateTime": "2025-12-22 08:59:53"
     }
   ],
-  "taskTreeUpdatedAt": "2026-09-30T05:00:09.166600+00:00",
+  "taskTreeUpdatedAt": "2026-09-30T05:03:35.758691+00:00",
   "version": 1
 }

.modelhub_state/outcome_checkpoint.json

@@ -1,6 +1,6 @@
 {
-  "generatedAt": "2026-09-30T02:54:55.839506+00:00",
+  "generatedAt": "2026-09-30T05:01:54.491674+00:00",
-  "lastSyncTime": "2026-09-30T02:54:55.570929+00:00",
+  "lastSyncTime": "2026-09-30T05:01:54.142796+00:00",
   "recentLimit": 300,
   "report": {
     "architectureCompatibilityBlocks": {
@@ -3452,24 +3452,24 @@
         "decisionSuccessRate": 0.1375,
         "decisionTotal": 80,
         "failureBreakdown": {
-          "ambiguous_runtime": 65,
+          "ambiguous_runtime": 66,
           "framework_architecture_unsupported": 64,
           "memory_capacity": 1,
           "repository_structure": 1,
           "tokenizer_compatibility": 3
         },
-        "failureCount": 134,
+        "failureCount": 135,
-        "failureRate": 0.9241,
+        "failureRate": 0.9247,
         "framework": "vllm",
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 11,
-        "successRate": 0.0759,
+        "successRate": 0.0753,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 145,
+        "total": 146,
-        "unresolvedFailureCount": 65
+        "unresolvedFailureCount": 66
       },
       "Ascend_910-b3|vllm|visual-multi-modal": {
         "attributableFailureCount": 1,
@@ -6001,7 +6001,7 @@
         "decisionSuccessRate": 0.0268,
         "decisionTotal": 3731,
         "failureBreakdown": {
-          "ambiguous_runtime": 1588,
+          "ambiguous_runtime": 1589,
           "architecture_compatibility": 112,
           "attention_backend": 3,
           "backend_operator": 93,
@@ -6015,15 +6015,15 @@
           "tokenizer_compatibility": 418,
           "参数/模板问题": 50
         },
-        "failureCount": 6142,
+        "failureCount": 6143,
         "failureRate": 0.984,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 873,
         "successCount": 100,
         "successRate": 0.016,
-        "total": 6242,
+        "total": 6243,
-        "unresolvedFailureCount": 1638
+        "unresolvedFailureCount": 1639
       },
       "vllm-customized": {
         "attributableFailureCount": 15,
@@ -6173,7 +6173,7 @@
         "unresolvedFailureCount": 207
       }
     },
-    "generatedAt": "2026-09-30T02:54:55.824115+00:00",
+    "generatedAt": "2026-09-30T05:01:54.433081+00:00",
     "gpuSummaries": {
       "Ascend_910-b3": {
         "attributableFailureCount": 105,
@@ -6181,7 +6181,7 @@
         "decisionSuccessRate": 0.1732,
         "decisionTotal": 127,
         "failureBreakdown": {
-          "ambiguous_runtime": 133,
+          "ambiguous_runtime": 134,
           "context_length": 6,
           "framework_architecture_unsupported": 93,
           "memory_capacity": 2,
@@ -6191,15 +6191,15 @@
           "日志缺失": 3,
           "验证失败": 27
         },
-        "failureCount": 307,
+        "failureCount": 308,
-        "failureRate": 0.9331,
+        "failureRate": 0.9333,
         "pendingCount": 0,
         "pendingRate": 0.0,
         "platformFailureCount": 0,
         "successCount": 22,
-        "successRate": 0.0669,
+        "successRate": 0.0667,
-        "total": 329,
+        "total": 330,
-        "unresolvedFailureCount": 202
+        "unresolvedFailureCount": 203
       },
       "Ascend_910-b4": {
         "attributableFailureCount": 325,
@@ -7537,9 +7537,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm",
         "modelType": "gemma3",
@@ -7551,8 +7551,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Ascend_910-b3|vllm|text-generation|gemma4|none": {
         "attributableFailureCount": 2,
@@ -23441,10 +23441,10 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 2,
         "failureBreakdown": {
-          "ambiguous_runtime": 3,
+          "ambiguous_runtime": 4,
           "framework_architecture_unsupported": 2
         },
-        "failureCount": 5,
+        "failureCount": 6,
         "failureRate": 1.0,
         "framework": "vllm",
         "lastPlatformFailureAt": null,
@@ -23456,8 +23456,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 5,
+        "total": 6,
-        "unresolvedFailureCount": 3
+        "unresolvedFailureCount": 4
       },
       "Ascend_910-b4|unknown|text-generation": {
         "attributableFailureCount": 0,
@@ -24191,9 +24191,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "参数/模板问题": 3
+          "参数/模板问题": 2
         },
-        "failureCount": 3,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "unknown",
         "lastPlatformFailureAt": null,
@@ -24205,8 +24205,8 @@
         "successRate": 0.0,
         "targetGpu": "hygon_k100-ai",
         "taskType": "text-generation",
-        "total": 3,
+        "total": 2,
-        "unresolvedFailureCount": 3
+        "unresolvedFailureCount": 2
       },
       "hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
         "attributableFailureCount": 5,
@@ -24314,6 +24314,31 @@
         "total": 2,
         "unresolvedFailureCount": 2
       },
+      "Ascend_910-b3|vllm|text-generation|gemma3|compressed-tensors": {
+        "attributableFailureCount": 0,
+        "consecutiveFailures": 0,
+        "decisionFailureRate": 0.0,
+        "decisionSuccessRate": 0.0,
+        "decisionTotal": 0,
+        "failureBreakdown": {
+          "ambiguous_runtime": 1
+        },
+        "failureCount": 1,
+        "failureRate": 1.0,
+        "framework": "vllm",
+        "lastTerminalAt": "2026-09-30T05:01:54.142796+00:00",
+        "modelType": "gemma3",
+        "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|text-generation|lfm2|none": {
         "attributableFailureCount": 0,
         "consecutiveFailures": 0,
@@ -28855,9 +28880,9 @@
         "decisionSuccessRate": 0.0,
         "decisionTotal": 0,
         "failureBreakdown": {
-          "ambiguous_runtime": 1
+          "ambiguous_runtime": 2
         },
-        "failureCount": 1,
+        "failureCount": 2,
         "failureRate": 1.0,
         "framework": "vllm",
         "loadSizeLog2Bucket": 34,
@@ -28870,8 +28895,8 @@
         "successRate": 0.0,
         "targetGpu": "Ascend_910-b3",
         "taskType": "text-generation",
-        "total": 1,
+        "total": 2,
-        "unresolvedFailureCount": 1
+        "unresolvedFailureCount": 2
       },
       "Ascend_910-b3|vllm|text-generation|gemma4|none|34": {
         "attributableFailureCount": 2,
@@ -53177,15 +53202,15 @@
         "unresolvedFailureCount": 0
       }
     },
-    "terminalRecords": 17139,
+    "terminalRecords": 17140,
-    "totalRecords": 17360,
+    "totalRecords": 17361,
     "totals": {
       "attributableFailureCount": 6141,
       "decisionFailureRate": 0.8633,
       "decisionSuccessRate": 0.1367,
       "decisionTotal": 7113,
       "failureBreakdown": {
-        "ambiguous_runtime": 4461,
+        "ambiguous_runtime": 4462,
         "architecture_compatibility": 212,
         "attention_backend": 3,
         "backend_operator": 128,
@@ -53201,15 +53226,15 @@
         "日志缺失": 719,
         "验证失败": 676
       },
-      "failureCount": 16167,
+      "failureCount": 16168,
       "failureRate": 0.9433,
       "pendingCount": 0,
       "pendingRate": 0.0,
       "platformFailureCount": 942,
       "successCount": 972,
       "successRate": 0.0567,
-      "total": 17139,
+      "total": 17140,
-      "unresolvedFailureCount": 9084
+      "unresolvedFailureCount": 9085
     },
     "warnings": [
       "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -53238,7 +53263,6 @@
       "组合 Kunlunxin_p-800|vllm_tokenizer_patch|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-b4|llamacpp|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|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
-      "组合 Kunlunxin_p-800|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 MetaX_c-500|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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x4|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -53264,10 +53288,11 @@
       "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
       "组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
-      "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 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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
     ]
   },
   "storageMode": "decision_state_only",
-  "summarizedRecords": 17360,
+  "summarizedRecords": 17361,
   "version": 1
 }

.modelhub_state/recent_outcomes.jsonl

@@ -227,6 +227,7 @@
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-23T18:55:34.958625+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499021, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020499021}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:33:50.394331+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997188", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-23T13:59:55.453747+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T08:31:34.413070+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997093", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T16:17:37.246200+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197700}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:29:25.979829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation", "verifyResult": -1}
+{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-30T05:01:54.142796+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:29:25.977872+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-23T18:18:45.361433+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T08:17:20.243727+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4996859", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-22T08:29:00.965161+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:11:51.336512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996820", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-23T15:01:41.955014+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:09:36.692226+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996782", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
 {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354826+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4080024", "taskType": "text-generation", "verifyResult": -1}
 {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446730+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860052", "taskType": "text-generation", "verifyResult": null}
 {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446754+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849007", "taskType": "text-generation", "verifyResult": null}
-{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446763+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860051", "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": "525ef81bf9710ea9ebf0b2f3492ddae64188795e8bb88aa964947e5b63532df2",
+    ".modelhub_state/architecture_compatibility_blacklist.json": "013a27717b143b61b061cef0d59be74d874383b8c8eb50f005b0a6b0050e46ad",
     ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
-    ".modelhub_state/market_intelligence.json": "f510cff1c9c1a09863a60e49e4fde0103eeff89f70a1fe11224b3d3d7a32a6e0",
+    ".modelhub_state/market_intelligence.json": "4b87bf564a37f99cce735c79316cb58a5bdd7590a88b9916e3b520b76f26e111",
-    ".modelhub_state/official_capabilities.json": "0b6250db87cac5576edfe3fcd851368ef9ef98458d8a7a032a060d0e8da2fe1d",
+    ".modelhub_state/official_capabilities.json": "15439acdd355f4e3472558b1d343cc1002771e302959f36197f4db7d29a7904d",
-    ".modelhub_state/outcome_checkpoint.json": "2b630c484014f1379844074e2f86ad65b21857cc54de1b4786a2f8cff6664460",
+    ".modelhub_state/outcome_checkpoint.json": "64fb0c33741c78338ae3b7e1eea192c3cf2864caad71d1bf63f59739755fbc71",
     ".modelhub_state/queue_cleanup_latest.json": "0d1ab1619c1619c7dc285dd028fe75c1691353037cec4ea9e2f66703792fefed",
-    ".modelhub_state/recent_outcomes.jsonl": "5854a9d6c2088f37329731f0343fdae6be2ecf4344fc5f8f1e0c5f4c6aa01c5c",
+    ".modelhub_state/recent_outcomes.jsonl": "06a8a7991dbab10b16766241949fc114215b825ff2eaf11917930d90fadd6df6",
-    ".modelhub_state/recovery_active_tasks.jsonl": "5740c453989a0ac56d05fe2700238a0d477403db82d1cdb74e4113f8291797c6",
+    ".modelhub_state/recovery_active_tasks.jsonl": "30f90e85882462d66f64005060d122c0cce5069ab98c83f5b1fea23ec8cc25a8",
-    ".modelhub_state/recovery_intents.jsonl": "e14bebfca8f9db3c0958e2c2509e64fd353e37c3844567dd9cca68b2354a7d56",
+    ".modelhub_state/recovery_intents.jsonl": "ff6f50fc994a91de80db18e658b5543702d37839def2428ff203af211a83cab6",
     ".modelhub_state/routing_intelligence.json": "e3b846e03b9cefff72d49f50d498c3789837242d91c64ca5c50562a1434a0cf5",
     ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
     ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06",
     "ledger/submissions.jsonl": "b12264c6ebf11ea6543e4652fb25f4c699076c224149219d8ab5fbf2a30205a1",
-    "outcomes/submissions.jsonl": "ffc9aa03d89bb83735fe79c70165e2d2b416694d55a8f6732e1893ca225869eb"
+    "outcomes/submissions.jsonl": "311b874f73aca05526f1276f25851c465f2aa5d9dc28478e9d674e5547ab0c7d"
   },
-  "generation": 18671,
+  "generation": 18672,
   "phase": "cycle",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-30T05:00:52.414930+00:00",
+  "updatedAt": "2026-09-30T05:06:38.501333+00:00",
   "writerId": "9d958b95ce4146c9939da0f14b9201ff"
 }

outcomes/submissions.jsonl

@@ -384,7 +384,6 @@
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:21:18.661350+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:03:06.665592+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4996702", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:21:18.661400+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499021, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020499021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:03:50.463371+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4996756", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:21:18.661372+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-T2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "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": 29326950127, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:text-to-image"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326950127}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:17:20.209866+00:00", "targetGpu": "Biren_166m", "taskId": "4996857", "taskType": "text-generation", "verifyResult": null}
-{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T16:50:30.559284+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:25.977872+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559229+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:25.981023+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997054", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559160+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 13603621925, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12247782400, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13603621925}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:48.235778+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997092", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559176+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-21T08:33:57.835795+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997190", "taskType": "text-generation", "verifyResult": null}