state: generation 11004 (cycle)
This commit is contained in:
@@ -2348,7 +2348,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T23:40:12.560184+00:00",
|
||||
"generatedAt": "2026-09-20T23:43:40.620101+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 115,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -425,7 +425,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T23:42:39.199945+00:00",
|
||||
"generatedAt": "2026-09-20T23:43:46.761393+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-20T23:42:39.199945+00:00",
|
||||
"catalogUpdatedAt": "2026-09-20T23:43:46.761393+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-20T23:42:39.199945+00:00",
|
||||
"generatedAt": "2026-09-20T23:43:46.761393+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6453,6 +6453,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-20T23:42:39.199945+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-20T23:43:46.761393+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T23:08:35.945810+00:00",
|
||||
"lastSyncTime": "2026-09-20T23:08:35.573495+00:00",
|
||||
"generatedAt": "2026-09-20T23:43:40.555993+00:00",
|
||||
"lastSyncTime": "2026-09-20T23:43:40.271809+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2719,15 +2719,15 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 138,
|
||||
"decisionFailureRate": 0.9324,
|
||||
"decisionSuccessRate": 0.0676,
|
||||
"decisionTotal": 148,
|
||||
"attributableFailureCount": 139,
|
||||
"decisionFailureRate": 0.9329,
|
||||
"decisionSuccessRate": 0.0671,
|
||||
"decisionTotal": 149,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 130,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 86,
|
||||
"framework_architecture_unsupported": 87,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 12,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -2738,7 +2738,7 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 572,
|
||||
"failureCount": 573,
|
||||
"failureRate": 0.9828,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
@@ -2748,7 +2748,7 @@
|
||||
"successRate": 0.0172,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 582,
|
||||
"total": 583,
|
||||
"unresolvedFailureCount": 432
|
||||
},
|
||||
"Biren_166m|unknown|visual-multi-modal": {
|
||||
@@ -4907,16 +4907,16 @@
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 1857,
|
||||
"decisionFailureRate": 0.6973,
|
||||
"decisionSuccessRate": 0.3027,
|
||||
"decisionTotal": 2663,
|
||||
"attributableFailureCount": 1858,
|
||||
"decisionFailureRate": 0.6974,
|
||||
"decisionSuccessRate": 0.3026,
|
||||
"decisionTotal": 2664,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1964,
|
||||
"architecture_compatibility": 100,
|
||||
"backend_operator": 5,
|
||||
"context_length": 157,
|
||||
"framework_architecture_unsupported": 628,
|
||||
"framework_architecture_unsupported": 629,
|
||||
"memory_capacity": 443,
|
||||
"model_load": 100,
|
||||
"platform_infrastructure": 42,
|
||||
@@ -4927,14 +4927,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 8305,
|
||||
"failureCount": 8306,
|
||||
"failureRate": 0.9115,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 42,
|
||||
"successCount": 806,
|
||||
"successRate": 0.0885,
|
||||
"total": 9111,
|
||||
"total": 9112,
|
||||
"unresolvedFailureCount": 6406
|
||||
},
|
||||
"vllm": {
|
||||
@@ -5102,7 +5102,7 @@
|
||||
"unresolvedFailureCount": 38
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T23:08:35.936002+00:00",
|
||||
"generatedAt": "2026-09-20T23:43:40.546565+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 87,
|
||||
@@ -5158,15 +5158,15 @@
|
||||
"unresolvedFailureCount": 596
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 177,
|
||||
"decisionFailureRate": 0.8762,
|
||||
"decisionSuccessRate": 0.1238,
|
||||
"decisionTotal": 202,
|
||||
"attributableFailureCount": 178,
|
||||
"decisionFailureRate": 0.8768,
|
||||
"decisionSuccessRate": 0.1232,
|
||||
"decisionTotal": 203,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 134,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 115,
|
||||
"framework_architecture_unsupported": 116,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 21,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -5177,14 +5177,14 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 616,
|
||||
"failureRate": 0.961,
|
||||
"failureCount": 617,
|
||||
"failureRate": 0.9611,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.039,
|
||||
"total": 641,
|
||||
"successRate": 0.0389,
|
||||
"total": 642,
|
||||
"unresolvedFailureCount": 437
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -13393,23 +13393,23 @@
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"model_load": 1,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T22:43:47.754964+00:00",
|
||||
"lastTerminalAt": "2026-09-20T23:43:40.271809+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -13417,7 +13417,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -13690,26 +13690,26 @@
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.375,
|
||||
"decisionSuccessRate": 0.625,
|
||||
"decisionTotal": 8,
|
||||
"decisionFailureRate": 0.4286,
|
||||
"decisionSuccessRate": 0.5714,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureRate": 0.4444,
|
||||
"failureRate": 0.5,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 5,
|
||||
"successRate": 0.5556,
|
||||
"successCount": 4,
|
||||
"successRate": 0.5,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -28555,20 +28555,20 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15998,
|
||||
"totalRecords": 16162,
|
||||
"terminalRecords": 15999,
|
||||
"totalRecords": 16163,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5817,
|
||||
"attributableFailureCount": 5818,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6749,
|
||||
"decisionTotal": 6750,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3823,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 318,
|
||||
"framework_architecture_unsupported": 2027,
|
||||
"framework_architecture_unsupported": 2028,
|
||||
"memory_capacity": 1197,
|
||||
"model_load": 485,
|
||||
"platform_infrastructure": 922,
|
||||
@@ -28579,14 +28579,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 15066,
|
||||
"failureCount": 15067,
|
||||
"failureRate": 0.9417,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 932,
|
||||
"successRate": 0.0583,
|
||||
"total": 15998,
|
||||
"total": 15999,
|
||||
"unresolvedFailureCount": 8327
|
||||
},
|
||||
"warnings": [
|
||||
@@ -28634,12 +28634,12 @@
|
||||
"组合 Cambricon_mlu-370-x4|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 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 Iluvatar_bi-150|transformers|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 Cambricon_mlu-370-x8|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|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 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16162,
|
||||
"summarizedRecords": 16163,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -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_moe"], "framework": "", "lastSyncTime": "2026-09-20T23:43:40.271809+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T23:43:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610385", "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": "2026-09-20T23:08:35.573428+00:00", "modelId": "YOYO-AI/ZYH-LLM-Qwen2.5-14B-V2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T23:05:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079190", "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": "2026-09-20T22:43:47.754964+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:31:23+00:00", "targetGpu": "Biren_166m", "taskId": "4610366", "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": "2026-09-20T22:20:31.465723+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:19:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4587221", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +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", "failureUnsupportedArchitectures": ["NanbeigeForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-15T22:50:36.100803+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T22:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609091", "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": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-15T22:04:09.314374+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T22:03:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4609077", "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": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-15T20:59:59.007477+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T20:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4576625", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T20:13:32.148467+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T20:09:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4588182", "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
Reference in New Issue
Block a user