state: generation 6560 (cycle)
This commit is contained in:
@@ -1454,7 +1454,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T05:48:52.432014+00:00",
|
||||
"generatedAt": "2026-09-13T05:51:51.722799+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 73,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 474,
|
||||
"listingErrors": 475,
|
||||
"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": "2026-09-13T05:48:52.406521+00:00",
|
||||
"updatedAt": "2026-09-13T05:51:51.694109+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-13T05:34:28.516080+00:00",
|
||||
"communityAttemptedAt": "2026-09-13T05:50:00.193790+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-13T05:34:28.516080+00:00",
|
||||
"communityUpdatedAt": "2026-09-13T05:50:00.193790+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-13T02:20:58.966988+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T05:47:29.558538+00:00",
|
||||
"generatedAt": "2026-09-13T05:50:00.193790+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T05:03:24.000102+00:00",
|
||||
"lastSyncTime": "2026-09-13T05:03:23.648984+00:00",
|
||||
"generatedAt": "2026-09-13T05:49:53.761779+00:00",
|
||||
"lastSyncTime": "2026-09-13T05:49:53.509642+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1936,30 +1936,30 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 92,
|
||||
"decisionFailureRate": 0.8598,
|
||||
"decisionSuccessRate": 0.1402,
|
||||
"decisionTotal": 107,
|
||||
"attributableFailureCount": 93,
|
||||
"decisionFailureRate": 0.8611,
|
||||
"decisionSuccessRate": 0.1389,
|
||||
"decisionTotal": 108,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"framework_architecture_unsupported": 50,
|
||||
"framework_architecture_unsupported": 51,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 41,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 163,
|
||||
"failureRate": 0.9157,
|
||||
"failureCount": 164,
|
||||
"failureRate": 0.9162,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0843,
|
||||
"successRate": 0.0838,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 178,
|
||||
"total": 179,
|
||||
"unresolvedFailureCount": 70
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
@@ -2463,14 +2463,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 150,
|
||||
"decisionFailureRate": 0.7353,
|
||||
"decisionSuccessRate": 0.2647,
|
||||
"decisionTotal": 204,
|
||||
"attributableFailureCount": 151,
|
||||
"decisionFailureRate": 0.7366,
|
||||
"decisionSuccessRate": 0.2634,
|
||||
"decisionTotal": 205,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 141,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 95,
|
||||
"framework_architecture_unsupported": 96,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 43,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2478,14 +2478,14 @@
|
||||
"参数/模板问题": 61,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1026,
|
||||
"failureCount": 1027,
|
||||
"failureRate": 0.95,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 54,
|
||||
"successRate": 0.05,
|
||||
"total": 1080,
|
||||
"total": 1081,
|
||||
"unresolvedFailureCount": 875
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2617,7 +2617,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T05:03:23.994548+00:00",
|
||||
"generatedAt": "2026-09-13T05:49:53.757657+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2781,27 +2781,27 @@
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 94,
|
||||
"decisionFailureRate": 0.8624,
|
||||
"decisionSuccessRate": 0.1376,
|
||||
"decisionTotal": 109,
|
||||
"attributableFailureCount": 95,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 110,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"framework_architecture_unsupported": 51,
|
||||
"framework_architecture_unsupported": 52,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 42,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 165,
|
||||
"failureRate": 0.9167,
|
||||
"failureCount": 166,
|
||||
"failureRate": 0.9171,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0833,
|
||||
"total": 180,
|
||||
"successRate": 0.0829,
|
||||
"total": 181,
|
||||
"unresolvedFailureCount": 70
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -4721,21 +4721,21 @@
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 12,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.7059,
|
||||
"decisionSuccessRate": 0.2941,
|
||||
"decisionTotal": 17,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 10
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 9
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.75,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-13T03:22:02.529638+00:00",
|
||||
"lastTerminalAt": "2026-09-13T05:49:53.509642+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -7462,17 +7462,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1765,
|
||||
"totalRecords": 1852,
|
||||
"terminalRecords": 1766,
|
||||
"totalRecords": 1853,
|
||||
"totals": {
|
||||
"attributableFailureCount": 511,
|
||||
"decisionFailureRate": 0.8965,
|
||||
"decisionSuccessRate": 0.1035,
|
||||
"decisionTotal": 570,
|
||||
"attributableFailureCount": 512,
|
||||
"decisionFailureRate": 0.8967,
|
||||
"decisionSuccessRate": 0.1033,
|
||||
"decisionTotal": 571,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 415,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 320,
|
||||
"framework_architecture_unsupported": 321,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 73,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7482,20 +7482,21 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1706,
|
||||
"failureCount": 1707,
|
||||
"failureRate": 0.9666,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0334,
|
||||
"total": 1765,
|
||||
"total": 1766,
|
||||
"unresolvedFailureCount": 1191
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 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 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -7504,7 +7505,6 @@
|
||||
"GPU MetaX_c-500 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 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。",
|
||||
"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。",
|
||||
"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 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。",
|
||||
@@ -7527,6 +7527,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1852,
|
||||
"summarizedRecords": 1853,
|
||||
"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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-13T05:49:53.509642+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T05:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549640", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T05:03:23.648954+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585193", "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": "", "lastSyncTime": "2026-09-13T04:23:07.613289+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:17:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4557614", "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": "2026-09-13T04:05:56.910845+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:05:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332432", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T11:08:33.010362+00:00", "modelId": "modelyoungyyds/SuperAI-v1-Mini", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:07:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332981", "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": "2026-09-09T11:08:33.010387+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460755", "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_mtp"], "framework": "", "lastSyncTime": "2026-09-09T11:01:57.287962+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T11:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332978", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-09T10:14:08.904917+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T10:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4421471", "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