state: generation 7612 (cycle)

This commit is contained in:
2026-09-15 09:05:45 +00:00
parent e22d9d6465
commit 81d45ac022
9 changed files with 2086 additions and 2086 deletions

View File

@@ -1589,7 +1589,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T09:02:40.969811+00:00",
"generatedAt": "2026-09-15T09:05:44.724270+00:00",
"summary": {
"activeBlockCount": 78,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 553,
"listingErrors": 554,
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-15T09:02:40.945919+00:00",
"updatedAt": "2026-09-15T09:05:44.698672+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T09:00:55.659924+00:00",
"generatedAt": "2026-09-15T09:03:48.531713+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-15T08:44:38.829584+00:00",
"lastSyncTime": "2026-09-15T08:44:38.534762+00:00",
"generatedAt": "2026-09-15T09:03:42.046409+00:00",
"lastSyncTime": "2026-09-15T09:03:41.806180+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2077,13 +2077,13 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 99,
"decisionFailureRate": 0.8684,
"decisionSuccessRate": 0.1316,
"decisionTotal": 114,
"attributableFailureCount": 100,
"decisionFailureRate": 0.8696,
"decisionSuccessRate": 0.1304,
"decisionTotal": 115,
"failureBreakdown": {
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 54,
"framework_architecture_unsupported": 55,
"memory_capacity": 1,
"model_load": 43,
"platform_infrastructure": 1,
@@ -2091,17 +2091,17 @@
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 173,
"failureRate": 0.9202,
"failureCount": 174,
"failureRate": 0.9206,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0798,
"successRate": 0.0794,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 188,
"total": 189,
"unresolvedFailureCount": 73
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2606,14 +2606,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 166,
"decisionFailureRate": 0.7444,
"decisionSuccessRate": 0.2556,
"decisionTotal": 223,
"attributableFailureCount": 167,
"decisionFailureRate": 0.7455,
"decisionSuccessRate": 0.2545,
"decisionTotal": 224,
"failureBreakdown": {
"ambiguous_runtime": 156,
"backend_operator": 4,
"framework_architecture_unsupported": 107,
"framework_architecture_unsupported": 108,
"memory_capacity": 5,
"model_load": 45,
"platform_infrastructure": 1,
@@ -2621,14 +2621,14 @@
"参数/模板问题": 66,
"验证失败": 673
},
"failureCount": 1062,
"failureCount": 1063,
"failureRate": 0.9491,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 57,
"successRate": 0.0509,
"total": 1119,
"total": 1120,
"unresolvedFailureCount": 895
},
"vllm": {
@@ -2764,7 +2764,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T08:44:38.824411+00:00",
"generatedAt": "2026-09-15T09:03:42.041766+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 40,
@@ -2930,13 +2930,13 @@
"unresolvedFailureCount": 48
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 102,
"decisionFailureRate": 0.8718,
"decisionSuccessRate": 0.1282,
"decisionTotal": 117,
"attributableFailureCount": 103,
"decisionFailureRate": 0.8729,
"decisionSuccessRate": 0.1271,
"decisionTotal": 118,
"failureBreakdown": {
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 56,
"framework_architecture_unsupported": 57,
"memory_capacity": 1,
"model_load": 44,
"platform_infrastructure": 1,
@@ -2944,14 +2944,14 @@
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 176,
"failureRate": 0.9215,
"failureCount": 177,
"failureRate": 0.9219,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0785,
"total": 191,
"successRate": 0.0781,
"total": 192,
"unresolvedFailureCount": 73
},
"Kunlunxin_p-800": {
@@ -5699,15 +5699,15 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 7,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 5,
"model_load": 6,
"framework_architecture_unsupported": 6,
"model_load": 5,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
@@ -5715,7 +5715,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T01:15:42.313690+00:00",
"lastTerminalAt": "2026-09-15T09:03:41.806180+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -9369,17 +9369,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1909,
"totalRecords": 2003,
"terminalRecords": 1910,
"totalRecords": 2004,
"totals": {
"attributableFailureCount": 587,
"decisionFailureRate": 0.8989,
"decisionSuccessRate": 0.1011,
"decisionTotal": 653,
"attributableFailureCount": 588,
"decisionFailureRate": 0.8991,
"decisionSuccessRate": 0.1009,
"decisionTotal": 654,
"failureBreakdown": {
"ambiguous_runtime": 460,
"backend_operator": 44,
"framework_architecture_unsupported": 381,
"framework_architecture_unsupported": 382,
"memory_capacity": 12,
"model_load": 78,
"platform_infrastructure": 7,
@@ -9389,14 +9389,14 @@
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1843,
"failureCount": 1844,
"failureRate": 0.9654,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 66,
"successRate": 0.0346,
"total": 1909,
"total": 1910,
"unresolvedFailureCount": 1249
},
"warnings": [
@@ -9435,6 +9435,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2003,
"summarizedRecords": 2004,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:03:41.806180+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:03:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4593341", "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": "2026-09-15T08:44:38.534762+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T08:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4595483", "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": "2026-09-15T08:35:00.090935+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T08:31:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4593061", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-15T06:27:13.910681+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:23:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4544266", "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": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:33:34.200761+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505106", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144205+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:09:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610359", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144180+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:05:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610355", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106911+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471974", "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