state: generation 8352 (cycle)

This commit is contained in:
2026-09-16 19:11:42 +00:00
parent 286596f9a4
commit f7c93af3c2
11 changed files with 2278 additions and 2236 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T19:00:52.733062+00:00",
"lastSyncTime": "2026-09-16T19:00:52.657033+00:00",
"generatedAt": "2026-09-16T19:09:34.844010+00:00",
"lastSyncTime": "2026-09-16T19:09:33.045375+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1928,51 +1928,51 @@
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 14,
"decisionFailureRate": 0.9333,
"decisionSuccessRate": 0.0667,
"decisionTotal": 15,
"attributableFailureCount": 15,
"decisionFailureRate": 0.9375,
"decisionSuccessRate": 0.0625,
"decisionTotal": 16,
"failureBreakdown": {
"framework_architecture_unsupported": 9,
"framework_architecture_unsupported": 10,
"model_load": 5
},
"failureCount": 14,
"failureRate": 0.9333,
"failureCount": 15,
"failureRate": 0.9375,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0667,
"successRate": 0.0625,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"total": 16,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.8788,
"decisionSuccessRate": 0.1212,
"decisionTotal": 33,
"attributableFailureCount": 30,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 107,
"failureRate": 0.964,
"failureCount": 108,
"failureRate": 0.9643,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.036,
"successRate": 0.0357,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 111,
"total": 112,
"unresolvedFailureCount": 78
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
@@ -2760,14 +2760,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 182,
"decisionFailureRate": 0.7429,
"decisionSuccessRate": 0.2571,
"decisionTotal": 245,
"attributableFailureCount": 183,
"decisionFailureRate": 0.7439,
"decisionSuccessRate": 0.2561,
"decisionTotal": 246,
"failureBreakdown": {
"ambiguous_runtime": 157,
"backend_operator": 4,
"framework_architecture_unsupported": 122,
"framework_architecture_unsupported": 123,
"memory_capacity": 5,
"model_load": 46,
"platform_infrastructure": 1,
@@ -2775,25 +2775,25 @@
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1086,
"failureCount": 1087,
"failureRate": 0.9452,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 63,
"successRate": 0.0548,
"total": 1149,
"total": 1150,
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 369,
"decisionFailureRate": 0.9609,
"decisionSuccessRate": 0.0391,
"decisionTotal": 384,
"attributableFailureCount": 370,
"decisionFailureRate": 0.961,
"decisionSuccessRate": 0.039,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 273,
"framework_architecture_unsupported": 274,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2802,14 +2802,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 624,
"failureRate": 0.9765,
"failureCount": 625,
"failureRate": 0.9766,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0235,
"total": 639,
"successRate": 0.0234,
"total": 640,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T19:00:52.725797+00:00",
"generatedAt": "2026-09-16T19:09:34.838356+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2971,51 +2971,51 @@
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.9434,
"decisionSuccessRate": 0.0566,
"decisionTotal": 53,
"attributableFailureCount": 51,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 36,
"framework_architecture_unsupported": 37,
"memory_capacity": 1,
"model_load": 8,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 109,
"failureRate": 0.9732,
"failureCount": 110,
"failureRate": 0.9735,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0268,
"total": 112,
"successRate": 0.0265,
"total": 113,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.8788,
"decisionSuccessRate": 0.1212,
"decisionTotal": 33,
"attributableFailureCount": 30,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 41,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 110,
"failureRate": 0.9649,
"failureCount": 111,
"failureRate": 0.9652,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.0351,
"total": 114,
"successRate": 0.0348,
"total": 115,
"unresolvedFailureCount": 81
},
"Cambricon_mlu-370-x8": {
@@ -3617,6 +3617,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6277,15 +6300,15 @@
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 2,
"attributableFailureCount": 10,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 8,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 9,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
@@ -6293,7 +6316,7 @@
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T14:13:00.205420+00:00",
"lastTerminalAt": "2026-09-16T19:09:33.045349+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6302,7 +6325,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 9
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -6573,11 +6596,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 6,
"tokenizer_compatibility": 1
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -6589,8 +6612,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 12
"total": 18,
"unresolvedFailureCount": 11
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -7262,6 +7285,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -10993,17 +11040,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2037,
"totalRecords": 2131,
"terminalRecords": 2039,
"totalRecords": 2133,
"totals": {
"attributableFailureCount": 655,
"decisionFailureRate": 0.8899,
"decisionSuccessRate": 0.1101,
"decisionTotal": 736,
"attributableFailureCount": 657,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 738,
"failureBreakdown": {
"ambiguous_runtime": 494,
"backend_operator": 45,
"framework_architecture_unsupported": 430,
"framework_architecture_unsupported": 432,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -11013,14 +11060,14 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1956,
"failureRate": 0.9602,
"failureCount": 1958,
"failureRate": 0.9603,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 81,
"successRate": 0.0398,
"total": 2037,
"successRate": 0.0397,
"total": 2039,
"unresolvedFailureCount": 1291
},
"warnings": [
@@ -11031,11 +11078,11 @@
"GPU Biren_166m 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 hygon_k100-ai 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 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 Ascend_910-b3 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 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 Biren_166m|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 Biren_166m|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_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -11060,6 +11107,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2131,
"summarizedRecords": 2133,
"version": 1
}