state: generation 17110 (cycle)

This commit is contained in:
2026-09-27 06:28:22 +00:00
parent 2dcf836ee9
commit 7c7751d4a6
9 changed files with 1586 additions and 1515 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-27T06:21:56.302873+00:00",
"lastSyncTime": "2026-09-27T06:21:55.975831+00:00",
"generatedAt": "2026-09-27T06:27:28.836651+00:00",
"lastSyncTime": "2026-09-27T06:27:28.565882+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3823,10 +3823,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3836,8 +3836,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 4,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 14,
@@ -5992,22 +5992,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 44,
"ambiguous_runtime": 45,
"framework_architecture_unsupported": 9,
"model_load": 3,
"platform_infrastructure": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 5
},
"failureCount": 64,
"failureCount": 65,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 64,
"unresolvedFailureCount": 49
"total": 65,
"unresolvedFailureCount": 50
},
"vllm-mlu": {
"attributableFailureCount": 28,
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-27T06:21:56.237524+00:00",
"generatedAt": "2026-09-27T06:27:28.823702+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6226,7 +6226,7 @@
"decisionSuccessRate": 0.0894,
"decisionTotal": 817,
"failureBreakdown": {
"ambiguous_runtime": 495,
"ambiguous_runtime": 496,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 297,
@@ -6239,15 +6239,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1597,
"failureCount": 1598,
"failureRate": 0.9563,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 73,
"successRate": 0.0437,
"total": 1670,
"unresolvedFailureCount": 837
"total": 1671,
"unresolvedFailureCount": 838
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 60,
@@ -10506,6 +10506,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|mpt|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -22833,6 +22856,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-27T06:27:28.565882+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -22867,10 +22915,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -22882,8 +22930,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 6
"total": 6,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -23836,6 +23884,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|mpt|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-27T06:27:28.565882+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -23986,31 +24059,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-24T05:11:42.061432+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -32802,6 +32850,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|mpt|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 33,
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-customized|text-generation|phi3|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -51171,15 +51243,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17057,
"totalRecords": 17278,
"terminalRecords": 17058,
"totalRecords": 17279,
"totals": {
"attributableFailureCount": 6114,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7080,
"failureBreakdown": {
"ambiguous_runtime": 4416,
"ambiguous_runtime": 4417,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -51195,15 +51267,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16091,
"failureCount": 16092,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17057,
"unresolvedFailureCount": 9039
"total": 17058,
"unresolvedFailureCount": 9040
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -51211,15 +51283,15 @@
"GPU Ascend_910-b4 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 MetaX_c-500 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 Vastai_va16 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 Ascend_910-b3 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 Biren_166m 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-100 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 Iluvatar_bi-150 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。",
"组合 Ascend_910-b3|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 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|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -51243,7 +51315,6 @@
"组合 Cambricon_mlu-370-x4|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 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 Vastai_va16|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 Iluvatar_mrv-100|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 Mthreads_s4000|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 Iluvatar_bi-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -51257,10 +51328,11 @@
"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 Kunlunxin_p-800|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 Iluvatar_bi-150|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 Iluvatar_bi-150|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 Vastai_va16|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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17278,
"summarizedRecords": 17279,
"version": 1
}