state: generation 4908 (cycle)
This commit is contained in:
@@ -1306,7 +1306,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T02:31:06.741357+00:00",
|
||||
"generatedAt": "2026-09-10T02:34:21.193510+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 65,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -51,7 +51,7 @@
|
||||
"4": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 349,
|
||||
"listingErrors": 350,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 4,
|
||||
"nextAccountIndex": 5,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T02:31:06.716011+00:00",
|
||||
"updatedAt": "2026-09-10T02:34:21.170277+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T02:29:36.673187+00:00",
|
||||
"generatedAt": "2026-09-10T02:32:31.832589+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T02:23:37.333475+00:00",
|
||||
"lastSyncTime": "2026-09-10T02:23:37.132500+00:00",
|
||||
"generatedAt": "2026-09-10T02:32:07.743588+00:00",
|
||||
"lastSyncTime": "2026-09-10T02:32:07.501704+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1379,12 +1379,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 26,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 41,
|
||||
"failureCount": 42,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1394,8 +1394,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 41,
|
||||
"unresolvedFailureCount": 15
|
||||
"total": 42,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Ascend_910-b4|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -1540,24 +1540,24 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 74,
|
||||
"failureRate": 0.9737,
|
||||
"failureCount": 75,
|
||||
"failureRate": 0.974,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0263,
|
||||
"successRate": 0.026,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 76,
|
||||
"unresolvedFailureCount": 54
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2289,7 +2289,7 @@
|
||||
"decisionSuccessRate": 0.2866,
|
||||
"decisionTotal": 164,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 99,
|
||||
"ambiguous_runtime": 100,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 84,
|
||||
"memory_capacity": 5,
|
||||
@@ -2298,15 +2298,15 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 945,
|
||||
"failureRate": 0.9526,
|
||||
"failureCount": 946,
|
||||
"failureRate": 0.9527,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 47,
|
||||
"successRate": 0.0474,
|
||||
"total": 992,
|
||||
"unresolvedFailureCount": 828
|
||||
"successRate": 0.0473,
|
||||
"total": 993,
|
||||
"unresolvedFailureCount": 829
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 227,
|
||||
@@ -2314,7 +2314,7 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 227,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 129,
|
||||
"ambiguous_runtime": 130,
|
||||
"backend_operator": 22,
|
||||
"framework_architecture_unsupported": 168,
|
||||
"memory_capacity": 6,
|
||||
@@ -2325,15 +2325,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 378,
|
||||
"failureCount": 379,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 378,
|
||||
"unresolvedFailureCount": 150
|
||||
"total": 379,
|
||||
"unresolvedFailureCount": 151
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2436,7 +2436,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T02:23:37.327574+00:00",
|
||||
"generatedAt": "2026-09-10T02:32:07.739281+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2444,22 +2444,22 @@
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 8,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 76,
|
||||
"failureRate": 0.987,
|
||||
"failureCount": 77,
|
||||
"failureRate": 0.9872,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.013,
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 50
|
||||
"successRate": 0.0128,
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 51
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 38,
|
||||
@@ -2516,21 +2516,21 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 74,
|
||||
"failureRate": 0.9737,
|
||||
"failureCount": 75,
|
||||
"failureRate": 0.974,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0263,
|
||||
"total": 76,
|
||||
"unresolvedFailureCount": 54
|
||||
"successRate": 0.026,
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -3939,14 +3939,14 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"ambiguous_runtime": 11,
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 13,
|
||||
"failureCount": 14,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T01:16:26.008857+00:00",
|
||||
"lastTerminalAt": "2026-09-10T02:32:07.501688+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -3954,8 +3954,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 10
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Ascend_910-b4|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4044,24 +4044,24 @@
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureRate": 0.75,
|
||||
"failureCount": 7,
|
||||
"failureRate": 0.7778,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T02:15:07.106855+00:00",
|
||||
"lastTerminalAt": "2026-09-10T02:32:07.501704+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.25,
|
||||
"successRate": 0.2222,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -4634,12 +4634,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 1,
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4651,8 +4651,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 6
|
||||
}
|
||||
},
|
||||
"recentProfileCombinationStats": {
|
||||
@@ -6765,15 +6765,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1482,
|
||||
"totalRecords": 1566,
|
||||
"terminalRecords": 1484,
|
||||
"totalRecords": 1568,
|
||||
"totals": {
|
||||
"attributableFailureCount": 391,
|
||||
"decisionFailureRate": 0.8907,
|
||||
"decisionSuccessRate": 0.1093,
|
||||
"decisionTotal": 439,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 274,
|
||||
"ambiguous_runtime": 276,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 267,
|
||||
"memory_capacity": 11,
|
||||
@@ -6785,21 +6785,21 @@
|
||||
"参数/模板问题": 94,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1434,
|
||||
"failureRate": 0.9676,
|
||||
"failureCount": 1436,
|
||||
"failureRate": 0.9677,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0324,
|
||||
"total": 1482,
|
||||
"unresolvedFailureCount": 1041
|
||||
"successRate": 0.0323,
|
||||
"total": 1484,
|
||||
"unresolvedFailureCount": 1043
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 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。",
|
||||
@@ -6807,7 +6807,7 @@
|
||||
"GPU hygon_k100-ai 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 Mthreads_s4000 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 Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x8|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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -6828,6 +6828,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1566,
|
||||
"summarizedRecords": 1568,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
100
|
||||
],
|
||||
"accounts": 12,
|
||||
"activeScanned": 1108,
|
||||
"activeScanned": 1101,
|
||||
"ageCleanupMode": "admission_only",
|
||||
"agePolicySkipped": {
|
||||
"cleanupDisabled": true,
|
||||
@@ -116,13 +116,13 @@
|
||||
"unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)",
|
||||
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
|
||||
},
|
||||
"architectureModelConfigsComplete": 146,
|
||||
"architectureModelConfigsComplete": 140,
|
||||
"architectureOnly": false,
|
||||
"architecturePolicySkipped": {
|
||||
"frameworkCatalogUnknown": 2,
|
||||
"frameworkContextUnknown": 483,
|
||||
"modelArchitectureUnknown": 157,
|
||||
"noMatchingBlock": 847,
|
||||
"frameworkContextUnknown": 438,
|
||||
"modelArchitectureUnknown": 162,
|
||||
"noMatchingBlock": 835,
|
||||
"partiallyBlockedFrameworkSet": 102,
|
||||
"runningMatchedProtected": 0,
|
||||
"submissionContextMismatch": 0,
|
||||
@@ -167,7 +167,7 @@
|
||||
},
|
||||
"repositorySizesComplete": 271,
|
||||
"skipped": {
|
||||
"fitsKnownCapacity": 1106,
|
||||
"fitsKnownCapacity": 1099,
|
||||
"gpuCapacityUnknown": 0,
|
||||
"repositorySizeUnknown": 2
|
||||
},
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T02:32:07.501704+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496940", "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": "2026-09-10T02:32:07.501688+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505091", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:23:37.132500+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483081", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T02:15:07.106855+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497062", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:59:31.241099+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481728", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -296,5 +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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-07T06:07:37.712062+00:00", "modelId": "AI-ModelScope/HackIDLE-NIST-Coder-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T06:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080003", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-07T06:07:37.712028+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080856", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-07T05:45:22.903421+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:43:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461506", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-07T05:45:22.903457+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080310", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"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", "lastSyncTime": "2026-09-07T05:31:35.012360+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:21:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459779", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "5fd5936dd5b1dcfd707415008cf711702d9457aa68139231a0a7d639f2169a9d",
|
||||
".modelhub_state/architecture_history_backfill.json": "bba5530e14919b965b4f8fd15cf6ca9410202834bc1a4c4f8012e5b7e3839f9a",
|
||||
".modelhub_state/market_intelligence.json": "85ff0a4bf180b6ef077ba825ce20d27d78f709e0a7cdee0dcccb449a71763d00",
|
||||
".modelhub_state/official_capabilities.json": "c0fbf8eda59a8df697774f38bbd515204e18b23e9fb466d224f020b10e4d89fd",
|
||||
".modelhub_state/outcome_checkpoint.json": "7eb4683b4257024afbd752749d51fe365b48774a8d3ebfc3543c4ac758a411d5",
|
||||
".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32",
|
||||
".modelhub_state/recent_outcomes.jsonl": "a3620ca09de4595b4e3f27987de44051b34a899cc70747449b591a6841c2dca3",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "93d4ab6b3e0a10fd61e44e995add1e7dff947e1603df186f4558de3f27f0b14f",
|
||||
".modelhub_state/recovery_intents.jsonl": "bde988b2163eea051650f806fc9ad257a97d0cbefdb5499fc96b995a71120743",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "ef406468921cd4166759e5e763f40158fbaaf32ef462c5bfb67258dd86302421",
|
||||
".modelhub_state/architecture_history_backfill.json": "3d3be0742ed157d65cd3aceaf2cba701de561139285b2943020c0c28d6c24aec",
|
||||
".modelhub_state/market_intelligence.json": "be1e4300f73db36f3de8532fcd441dcd2f8911316cd860f665260a32bd72da2e",
|
||||
".modelhub_state/official_capabilities.json": "9716cd87aefa46868d91d6bacf83eb4bffa2200a84d74a0abd1bac417bafaa3b",
|
||||
".modelhub_state/outcome_checkpoint.json": "90be78f7c44eaa3829f98e45ec0fa3982431b76904ac599aeae7c67346ec18fd",
|
||||
".modelhub_state/queue_cleanup_latest.json": "1ff9cf1dcc1b2c2557b532394e1e76da55fa710317d6832581664c56c6ecc7b3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "9863bdbefbef04e14ac3e1578ca87fa3f1d850c18458c818ba3c6014b13524cf",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "93abb99c7e47b4a7a412477b1dd60c5c3e9a9a3edde359f77e50855605ed4f22",
|
||||
".modelhub_state/recovery_intents.jsonl": "a039f332cbb0de573f47b92b35eaf0441621e04fcc97bbd067c32abeda2ccef1",
|
||||
".modelhub_state/routing_intelligence.json": "289584603011b6a895f3ab1c0b743c174293ab94ad8d2f1f5a3531e01a72207b",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "d242179d528ce949e36ac1834a20e4f46e6d5194c7a834b19b8e1b58d9a1bea6",
|
||||
"outcomes/submissions.jsonl": "357d6a5de0d21a39daee132a9bcdb79b003c924c486ab5a4a06fded4f86da82e"
|
||||
"outcomes/submissions.jsonl": "aa4777b88adb640cc19bee1b1611d6a4701b470fc709ec54f48c2db876528cb5"
|
||||
},
|
||||
"generation": 4907,
|
||||
"generation": 4908,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T02:31:06.835228+00:00",
|
||||
"updatedAt": "2026-09-10T02:34:21.875434+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
@@ -510,7 +510,7 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T01:42:34.770227+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:36:33.499638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4743919", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T01:59:31.241046+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:53:28.482893+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T02:15:07.106881+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T18:11:56.418165+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4744370", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T18:31:44.217327+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4744546", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T02:32:07.501649+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T18:31:44.217327+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4744546", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 35648665467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T21:08:22.089453+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746439", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T21:08:22.086828+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746438", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838972, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838972}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-09T21:08:22.085342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746443", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user