state: generation 13298 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-23T02:31:29.894121+00:00",
|
||||
"lastSyncTime": "2026-09-23T02:31:28.170137+00:00",
|
||||
"generatedAt": "2026-09-23T02:35:36.757931+00:00",
|
||||
"lastSyncTime": "2026-09-23T02:35:34.755698+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4729,17 +4729,17 @@
|
||||
"unresolvedFailureCount": 19
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation": {
|
||||
"attributableFailureCount": 12,
|
||||
"attributableFailureCount": 13,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 12,
|
||||
"decisionTotal": 13,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"model_load": 1,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 14,
|
||||
"failureCount": 15,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -4749,7 +4749,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 14,
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Kunlunxin_r-200-8f|unknown|text-generation": {
|
||||
@@ -5712,15 +5712,15 @@
|
||||
"unresolvedFailureCount": 6462
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3574,
|
||||
"attributableFailureCount": 3575,
|
||||
"decisionFailureRate": 0.9741,
|
||||
"decisionSuccessRate": 0.0259,
|
||||
"decisionTotal": 3669,
|
||||
"decisionTotal": 3670,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1534,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 86,
|
||||
"backend_operator": 87,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1330,
|
||||
"memory_capacity": 722,
|
||||
@@ -5731,14 +5731,14 @@
|
||||
"tokenizer_compatibility": 413,
|
||||
"参数/模板问题": 48
|
||||
},
|
||||
"failureCount": 6022,
|
||||
"failureCount": 6023,
|
||||
"failureRate": 0.9845,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 866,
|
||||
"successCount": 95,
|
||||
"successRate": 0.0155,
|
||||
"total": 6117,
|
||||
"total": 6118,
|
||||
"unresolvedFailureCount": 1582
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5888,7 +5888,7 @@
|
||||
"unresolvedFailureCount": 175
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-23T02:31:29.882498+00:00",
|
||||
"generatedAt": "2026-09-23T02:35:36.744395+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6114,13 +6114,13 @@
|
||||
"unresolvedFailureCount": 717
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 53,
|
||||
"decisionFailureRate": 0.9138,
|
||||
"decisionSuccessRate": 0.0862,
|
||||
"decisionTotal": 58,
|
||||
"attributableFailureCount": 54,
|
||||
"decisionFailureRate": 0.9153,
|
||||
"decisionSuccessRate": 0.0847,
|
||||
"decisionTotal": 59,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 210,
|
||||
"backend_operator": 10,
|
||||
"backend_operator": 11,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 2,
|
||||
"model_load": 13,
|
||||
@@ -6131,14 +6131,14 @@
|
||||
"日志缺失": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 320,
|
||||
"failureRate": 0.9846,
|
||||
"failureCount": 321,
|
||||
"failureRate": 0.9847,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0154,
|
||||
"total": 325,
|
||||
"successRate": 0.0153,
|
||||
"total": 326,
|
||||
"unresolvedFailureCount": 266
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
@@ -17678,14 +17678,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2
|
||||
"backend_operator": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "starcoder2",
|
||||
@@ -17697,7 +17697,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|aquila3|none": {
|
||||
@@ -20888,9 +20888,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16
|
||||
"ambiguous_runtime": 15
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureCount": 15,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -20902,8 +20902,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 16
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 15
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
@@ -21141,18 +21141,18 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -21164,7 +21164,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
@@ -23005,9 +23005,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastTerminalAt": "2026-09-21T05:42:03.443562+00:00",
|
||||
@@ -23020,8 +23020,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-100|transformers|text-generation|mistral3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -24150,18 +24150,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2
|
||||
"backend_operator": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-22T08:25:19.951625+00:00",
|
||||
"lastTerminalAt": "2026-09-23T02:35:34.755698+00:00",
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
@@ -24171,7 +24171,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|llama|compressed-tensors": {
|
||||
@@ -41372,6 +41372,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|aquila3|none|12": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -45802,18 +45826,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16795,
|
||||
"totalRecords": 17013,
|
||||
"terminalRecords": 16796,
|
||||
"totalRecords": 17014,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6012,
|
||||
"attributableFailureCount": 6013,
|
||||
"decisionFailureRate": 0.8622,
|
||||
"decisionSuccessRate": 0.1378,
|
||||
"decisionTotal": 6973,
|
||||
"decisionTotal": 6974,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4283,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 114,
|
||||
"backend_operator": 115,
|
||||
"context_length": 322,
|
||||
"framework_architecture_unsupported": 2132,
|
||||
"memory_capacity": 1203,
|
||||
@@ -45826,19 +45850,20 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 15834,
|
||||
"failureCount": 15835,
|
||||
"failureRate": 0.9428,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 931,
|
||||
"successCount": 961,
|
||||
"successRate": 0.0572,
|
||||
"total": 16795,
|
||||
"total": 16796,
|
||||
"unresolvedFailureCount": 8891
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 Biren_166m 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 Cambricon_mlu-370-x8 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。",
|
||||
@@ -45849,7 +45874,6 @@
|
||||
"GPU Vastai_va16 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 Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -45873,7 +45897,6 @@
|
||||
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|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。",
|
||||
"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 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm_fix_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 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -45887,10 +45910,11 @@
|
||||
"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|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 MetaX_c-500|vllm|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 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 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-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": 17013,
|
||||
"summarizedRecords": 17014,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user