state: generation 5337 (cycle)

This commit is contained in:
2026-09-10 19:59:09 +00:00
parent 40a682f3c1
commit 3e334c183e
9 changed files with 1972 additions and 1997 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T19:48:10.294794+00:00",
"lastSyncTime": "2026-09-10T19:48:09.995356+00:00",
"generatedAt": "2026-09-10T19:56:52.084081+00:00",
"lastSyncTime": "2026-09-10T19:56:51.309700+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1794,7 +1794,7 @@
"decisionSuccessRate": 0.1163,
"decisionTotal": 86,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 27,
@@ -1802,18 +1802,18 @@
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 143,
"failureRate": 0.9346,
"failureCount": 144,
"failureRate": 0.9351,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0654,
"successRate": 0.0649,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 153,
"unresolvedFailureCount": 66
"total": 154,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -2142,12 +2142,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 58,
"ambiguous_runtime": 59,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 102,
"failureCount": 103,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2157,8 +2157,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 102,
"unresolvedFailureCount": 58
"total": 103,
"unresolvedFailureCount": 59
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2295,7 +2295,7 @@
"decisionSuccessRate": 0.2697,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 123,
"ambiguous_runtime": 124,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
@@ -2305,15 +2305,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 983,
"failureRate": 0.9534,
"failureCount": 984,
"failureRate": 0.9535,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0466,
"total": 1031,
"unresolvedFailureCount": 852
"successRate": 0.0465,
"total": 1032,
"unresolvedFailureCount": 853
},
"vllm": {
"attributableFailureCount": 240,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 185,
"ambiguous_runtime": 186,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 450,
"failureCount": 451,
"failureRate": 0.9956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0044,
"total": 452,
"unresolvedFailureCount": 209
"total": 453,
"unresolvedFailureCount": 210
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T19:48:10.290792+00:00",
"generatedAt": "2026-09-10T19:56:52.079960+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2611,7 +2611,7 @@
"decisionSuccessRate": 0.1163,
"decisionTotal": 86,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 27,
@@ -2619,15 +2619,15 @@
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 143,
"failureRate": 0.9346,
"failureCount": 144,
"failureRate": 0.9351,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0654,
"total": 153,
"unresolvedFailureCount": 66
"successRate": 0.0649,
"total": 154,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
"attributableFailureCount": 1,
@@ -2729,22 +2729,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 60,
"ambiguous_runtime": 61,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 250,
"failureRate": 0.9506,
"failureCount": 251,
"failureRate": 0.9508,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0494,
"total": 263,
"unresolvedFailureCount": 203
"successRate": 0.0492,
"total": 264,
"unresolvedFailureCount": 204
},
"hygon_k100-ai": {
"attributableFailureCount": 39,
@@ -4163,18 +4163,17 @@
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 2,
"参数/模板问题": 1
"framework_architecture_unsupported": 1
},
"failureCount": 6,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4186,8 +4185,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 4
"total": 4,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4271,28 +4270,29 @@
"attributableFailureCount": 17,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 8,
"model_load": 9,
"platform_infrastructure": 1
},
"failureCount": 18,
"failureRate": 0.9,
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T19:38:05.602511+00:00",
"lastTerminalAt": "2026-09-10T19:56:51.309700+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.1,
"successCount": 1,
"successRate": 0.05,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 0
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4539,7 +4539,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T19:48:09.995356+00:00",
"lastTerminalAt": "2026-09-10T19:56:51.309666+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4656,31 +4656,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T18:40:55.416623+00:00",
"modelType": "qwen3_5_mtp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -7020,15 +6995,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1628,
"totalRecords": 1715,
"terminalRecords": 1630,
"totalRecords": 1717,
"totals": {
"attributableFailureCount": 425,
"decisionFailureRate": 0.891,
"decisionSuccessRate": 0.109,
"decisionTotal": 477,
"failureBreakdown": {
"ambiguous_runtime": 376,
"ambiguous_runtime": 378,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -7040,31 +7015,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1576,
"failureCount": 1578,
"failureRate": 0.9681,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.0319,
"total": 1628,
"unresolvedFailureCount": 1147
"total": 1630,
"unresolvedFailureCount": 1149
},
"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。",
@@ -7079,10 +7053,11 @@
"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": 1715,
"summarizedRecords": 1717,
"version": 1
}