state: generation 10628 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T14:32:15.633088+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:32:15.260773+00:00",
|
||||
"generatedAt": "2026-09-20T14:34:58.328009+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:34:57.856745+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2889,13 +2889,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"pendingCount": 0,
|
||||
@@ -2905,8 +2905,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|unknown|asr": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -3411,25 +3411,25 @@
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 14,
|
||||
"decisionFailureRate": 0.56,
|
||||
"decisionSuccessRate": 0.44,
|
||||
"decisionTotal": 25,
|
||||
"decisionFailureRate": 0.5385,
|
||||
"decisionSuccessRate": 0.4615,
|
||||
"decisionTotal": 26,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 13,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.6207,
|
||||
"failureRate": 0.6,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 11,
|
||||
"successRate": 0.3793,
|
||||
"successCount": 12,
|
||||
"successRate": 0.4,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 29,
|
||||
"total": 30,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -4406,21 +4406,21 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 13,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 38,
|
||||
"ambiguous_runtime": 39,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
},
|
||||
"failureCount": 51,
|
||||
"failureCount": 52,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 51,
|
||||
"unresolvedFailureCount": 38
|
||||
"total": 52,
|
||||
"unresolvedFailureCount": 39
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 1856,
|
||||
@@ -4455,9 +4455,9 @@
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3474,
|
||||
"decisionFailureRate": 0.978,
|
||||
"decisionSuccessRate": 0.022,
|
||||
"decisionTotal": 3552,
|
||||
"decisionFailureRate": 0.9778,
|
||||
"decisionSuccessRate": 0.0222,
|
||||
"decisionTotal": 3553,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1431,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -4474,13 +4474,13 @@
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5809,
|
||||
"failureRate": 0.9868,
|
||||
"failureRate": 0.9866,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 78,
|
||||
"successRate": 0.0132,
|
||||
"total": 5887,
|
||||
"successCount": 79,
|
||||
"successRate": 0.0134,
|
||||
"total": 5888,
|
||||
"unresolvedFailureCount": 1471
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -4614,7 +4614,7 @@
|
||||
"unresolvedFailureCount": 24
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T14:32:15.624688+00:00",
|
||||
"generatedAt": "2026-09-20T14:34:58.319961+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 75,
|
||||
@@ -4781,7 +4781,7 @@
|
||||
"decisionSuccessRate": 0.1701,
|
||||
"decisionTotal": 876,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 603,
|
||||
"ambiguous_runtime": 604,
|
||||
"architecture_compatibility": 15,
|
||||
"backend_operator": 11,
|
||||
"context_length": 29,
|
||||
@@ -4796,21 +4796,21 @@
|
||||
"日志缺失": 155,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 1855,
|
||||
"failureRate": 0.9256,
|
||||
"failureCount": 1856,
|
||||
"failureRate": 0.9257,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 21,
|
||||
"successCount": 149,
|
||||
"successRate": 0.0744,
|
||||
"total": 2004,
|
||||
"unresolvedFailureCount": 1107
|
||||
"successRate": 0.0743,
|
||||
"total": 2005,
|
||||
"unresolvedFailureCount": 1108
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 964,
|
||||
"decisionFailureRate": 0.8486,
|
||||
"decisionSuccessRate": 0.1514,
|
||||
"decisionTotal": 1136,
|
||||
"decisionFailureRate": 0.8478,
|
||||
"decisionSuccessRate": 0.1522,
|
||||
"decisionTotal": 1137,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 344,
|
||||
"architecture_compatibility": 47,
|
||||
@@ -4828,13 +4828,13 @@
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 1684,
|
||||
"failureRate": 0.9073,
|
||||
"failureRate": 0.9068,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 7,
|
||||
"successCount": 172,
|
||||
"successRate": 0.0927,
|
||||
"total": 1856,
|
||||
"successCount": 173,
|
||||
"successRate": 0.0932,
|
||||
"total": 1857,
|
||||
"unresolvedFailureCount": 713
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -7061,6 +7061,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|mistral3|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -8423,24 +8446,24 @@
|
||||
"Iluvatar_mrv-100|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"failureRate": 0.5,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.5,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|llama|none": {
|
||||
@@ -11283,13 +11306,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -11301,8 +11324,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
@@ -11622,19 +11645,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
|
||||
@@ -11646,7 +11668,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -12002,6 +12024,31 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastTerminalAt": "2026-09-20T14:34:57.856723+00:00",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|mistral3|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -15988,6 +16035,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|llama|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|mistral3|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -17971,6 +18042,28 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|llama|awq|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|llama|awq|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -22102,15 +22195,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15868,
|
||||
"totalRecords": 15973,
|
||||
"terminalRecords": 15870,
|
||||
"totalRecords": 15975,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5755,
|
||||
"decisionFailureRate": 0.8615,
|
||||
"decisionSuccessRate": 0.1385,
|
||||
"decisionTotal": 6680,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6681,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3764,
|
||||
"ambiguous_runtime": 3765,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
@@ -22126,15 +22219,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14943,
|
||||
"failureCount": 14944,
|
||||
"failureRate": 0.9417,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 925,
|
||||
"successCount": 926,
|
||||
"successRate": 0.0583,
|
||||
"total": 15868,
|
||||
"unresolvedFailureCount": 8266
|
||||
"total": 15870,
|
||||
"unresolvedFailureCount": 8267
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -22179,12 +22272,12 @@
|
||||
"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": 15973,
|
||||
"summarizedRecords": 15975,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user