state: generation 11757 (cycle_no_slots)

This commit is contained in:
2026-09-21 21:08:32 +00:00
parent 6d8d438252
commit 3954c52474
7 changed files with 2029 additions and 1933 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T21:06:12.032617+00:00",
"lastSyncTime": "2026-09-21T21:06:10.459751+00:00",
"generatedAt": "2026-09-21T21:08:12.512892+00:00",
"lastSyncTime": "2026-09-21T21:08:12.157607+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4411,26 +4411,26 @@
"unresolvedFailureCount": 57
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 17,
"decisionFailureRate": 0.5484,
"decisionSuccessRate": 0.4516,
"decisionTotal": 31,
"attributableFailureCount": 18,
"decisionFailureRate": 0.5625,
"decisionSuccessRate": 0.4375,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 16,
"model_load": 1
"model_load": 2
},
"failureCount": 24,
"failureRate": 0.6316,
"failureCount": 25,
"failureRate": 0.641,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.3684,
"successRate": 0.359,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 38,
"total": 39,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -5506,10 +5506,10 @@
"unresolvedFailureCount": 6446
},
"vllm": {
"attributableFailureCount": 3544,
"attributableFailureCount": 3545,
"decisionFailureRate": 0.9758,
"decisionSuccessRate": 0.0242,
"decisionTotal": 3632,
"decisionTotal": 3633,
"failureBreakdown": {
"ambiguous_runtime": 1498,
"architecture_compatibility": 112,
@@ -5518,21 +5518,21 @@
"context_length": 161,
"framework_architecture_unsupported": 1311,
"memory_capacity": 722,
"model_load": 207,
"model_load": 208,
"platform_infrastructure": 865,
"repository_structure": 470,
"runtime_memory": 64,
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5953,
"failureCount": 5954,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6041,
"total": 6042,
"unresolvedFailureCount": 1544
},
"vllm-customized": {
@@ -5679,7 +5679,7 @@
"unresolvedFailureCount": 119
}
},
"generatedAt": "2026-09-21T21:06:12.021842+00:00",
"generatedAt": "2026-09-21T21:08:12.500869+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5873,10 +5873,10 @@
"unresolvedFailureCount": 1128
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 967,
"decisionFailureRate": 0.8468,
"decisionSuccessRate": 0.1532,
"decisionTotal": 1142,
"attributableFailureCount": 968,
"decisionFailureRate": 0.8469,
"decisionSuccessRate": 0.1531,
"decisionTotal": 1143,
"failureBreakdown": {
"ambiguous_runtime": 347,
"architecture_compatibility": 47,
@@ -5884,7 +5884,7 @@
"context_length": 77,
"framework_architecture_unsupported": 288,
"memory_capacity": 219,
"model_load": 85,
"model_load": 86,
"platform_infrastructure": 7,
"repository_structure": 133,
"runtime_memory": 1,
@@ -5893,14 +5893,14 @@
"日志缺失": 6,
"验证失败": 47
},
"failureCount": 1690,
"failureCount": 1691,
"failureRate": 0.9062,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 175,
"successRate": 0.0938,
"total": 1865,
"total": 1866,
"unresolvedFailureCount": 716
},
"Kunlunxin_p-800": {
@@ -13825,6 +13825,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -17700,9 +17723,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 3
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -17714,8 +17737,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 5,
@@ -18090,6 +18113,31 @@
"total": 3,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T21:08:12.157607+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18430,9 +18478,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T19:17:35.577982+00:00",
@@ -18445,8 +18493,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -21331,6 +21379,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T21:08:12.157607+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -32533,6 +32606,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 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": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -38232,13 +38329,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16416,
"totalRecords": 16610,
"terminalRecords": 16417,
"totalRecords": 16611,
"totals": {
"attributableFailureCount": 5919,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6867,
"attributableFailureCount": 5920,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6868,
"failureBreakdown": {
"ambiguous_runtime": 4040,
"architecture_compatibility": 212,
@@ -38247,7 +38344,7 @@
"context_length": 321,
"framework_architecture_unsupported": 2092,
"memory_capacity": 1199,
"model_load": 499,
"model_load": 500,
"platform_infrastructure": 925,
"repository_structure": 739,
"runtime_memory": 85,
@@ -38256,31 +38353,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15468,
"failureCount": 15469,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 948,
"successRate": 0.0577,
"total": 16416,
"total": 16417,
"unresolvedFailureCount": 8624
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 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。",
"GPU Sunrise_pt-200-x1 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 Vastai_va16 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_bi-150 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 Ascend_910-b4 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 MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|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 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 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。",
@@ -38320,6 +38417,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16610,
"summarizedRecords": 16611,
"version": 1
}