state: generation 5961 (cycle)

This commit is contained in:
2026-09-12 01:27:59 +00:00
parent f179c4686c
commit 128fe490d6
10 changed files with 2296 additions and 2296 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T01:24:56.571209+00:00",
"generatedAt": "2026-09-12T01:27:59.007804+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 427,
"listingErrors": 428,
"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": 8,
"nextAccountIndex": 9,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T01:24:56.548153+00:00",
"updatedAt": "2026-09-12T01:27:58.984862+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T01:23:05.953415+00:00",
"generatedAt": "2026-09-12T01:26:04.975523+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": "2026-09-12T00:52:00.246547+00:00",
"lastSyncTime": "2026-09-12T00:52:00.210563+00:00",
"generatedAt": "2026-09-12T01:25:57.550819+00:00",
"lastSyncTime": "2026-09-12T01:25:57.322172+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1762,18 +1762,18 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 15,
"attributableFailureCount": 16,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 8,
"framework_architecture_unsupported": 9,
"model_load": 3,
"runtime_memory": 2
},
"failureCount": 22,
"failureCount": 23,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1783,34 +1783,34 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 22,
"total": 23,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 87,
"decisionFailureRate": 0.8788,
"decisionSuccessRate": 0.1212,
"decisionTotal": 99,
"attributableFailureCount": 88,
"decisionFailureRate": 0.88,
"decisionSuccessRate": 0.12,
"decisionTotal": 100,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 37,
"model_load": 38,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 156,
"failureRate": 0.9286,
"failureCount": 157,
"failureRate": 0.929,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 12,
"successRate": 0.0714,
"successRate": 0.071,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 168,
"total": 169,
"unresolvedFailureCount": 68
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2311,40 +2311,40 @@
"unresolvedFailureCount": 6
},
"unknown": {
"attributableFailureCount": 141,
"decisionFailureRate": 0.7344,
"decisionSuccessRate": 0.2656,
"decisionTotal": 192,
"attributableFailureCount": 142,
"decisionFailureRate": 0.7358,
"decisionSuccessRate": 0.2642,
"decisionTotal": 193,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"framework_architecture_unsupported": 90,
"memory_capacity": 5,
"model_load": 39,
"model_load": 40,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1004,
"failureCount": 1005,
"failureRate": 0.9517,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 51,
"successRate": 0.0483,
"total": 1055,
"total": 1056,
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 244,
"attributableFailureCount": 245,
"decisionFailureRate": 0.9879,
"decisionSuccessRate": 0.0121,
"decisionTotal": 247,
"decisionTotal": 248,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
"framework_architecture_unsupported": 171,
"framework_architecture_unsupported": 172,
"memory_capacity": 6,
"model_load": 19,
"platform_infrastructure": 1,
@@ -2353,14 +2353,14 @@
"tokenizer_compatibility": 4,
"参数/模板问题": 24
},
"failureCount": 464,
"failureCount": 465,
"failureRate": 0.9936,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0064,
"total": 467,
"total": 468,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2464,7 +2464,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T00:52:00.242533+00:00",
"generatedAt": "2026-09-12T01:25:57.546677+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2603,51 +2603,51 @@
"unresolvedFailureCount": 27
},
"Iluvatar_bi-150": {
"attributableFailureCount": 20,
"decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2857,
"decisionTotal": 28,
"attributableFailureCount": 21,
"decisionFailureRate": 0.7241,
"decisionSuccessRate": 0.2759,
"decisionTotal": 29,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"framework_architecture_unsupported": 9,
"framework_architecture_unsupported": 10,
"model_load": 4,
"runtime_memory": 2,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 64,
"failureRate": 0.8889,
"failureCount": 65,
"failureRate": 0.8904,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1111,
"total": 72,
"successRate": 0.1096,
"total": 73,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 88,
"decisionFailureRate": 0.88,
"decisionSuccessRate": 0.12,
"decisionTotal": 100,
"attributableFailureCount": 89,
"decisionFailureRate": 0.8812,
"decisionSuccessRate": 0.1188,
"decisionTotal": 101,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 38,
"model_load": 39,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 157,
"failureRate": 0.929,
"failureCount": 158,
"failureRate": 0.9294,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 12,
"successRate": 0.071,
"total": 169,
"successRate": 0.0706,
"total": 170,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
@@ -4303,22 +4303,22 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T20:03:23.495341+00:00",
"lastTerminalAt": "2026-09-12T01:25:57.322124+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4326,30 +4326,29 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 0,
"attributableFailureCount": 16,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 17,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 2,
"model_load": 13,
"platform_infrastructure": 1
"model_load": 14
},
"failureCount": 18,
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-12T00:52:00.210542+00:00",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T01:25:57.322172+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1,
"targetGpu": "Iluvatar_mrv-100",
@@ -4365,9 +4364,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 3
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4379,8 +4378,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -7055,19 +7054,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1670,
"totalRecords": 1757,
"terminalRecords": 1672,
"totalRecords": 1759,
"totals": {
"attributableFailureCount": 442,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 498,
"attributableFailureCount": 444,
"decisionFailureRate": 0.888,
"decisionSuccessRate": 0.112,
"decisionTotal": 500,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 40,
"framework_architecture_unsupported": 276,
"framework_architecture_unsupported": 277,
"memory_capacity": 11,
"model_load": 62,
"model_load": 63,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -7075,31 +7074,30 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1614,
"failureCount": 1616,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0335,
"total": 1670,
"total": 1672,
"unresolvedFailureCount": 1168
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 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 MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU 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。",
"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-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 Mthreads_s4000|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-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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7114,10 +7112,11 @@
"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 Iluvatar_bi-150|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 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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1757,
"summarizedRecords": 1759,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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", "framework": "vllm", "lastSyncTime": "2026-09-12T01:25:57.322124+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T01:25:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079965", "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": "2026-09-12T01:25:57.322172+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T01:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523213", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T00:52:00.210542+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T00:49:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523319", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207568+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079945", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207605+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079258", "taskType": "text-generation", "verifyResult": null}
@@ -296,5 +298,3 @@
{"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", "framework": "vllm", "lastSyncTime": "2026-09-08T12:11:42.795288+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:07:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080027", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T12:11:42.795279+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080026", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T11:42:26.289451+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:35:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4007714", "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": "2026-09-08T11:42:26.289433+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:25:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4483789", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T11:18:26.601995+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079157", "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