state: generation 8768 (cycle)

This commit is contained in:
2026-09-17 14:09:15 +00:00
parent ca7f5c8bb6
commit bc16b5c97d
9 changed files with 1845 additions and 1845 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T13:48:00.836610+00:00",
"lastSyncTime": "2026-09-17T13:48:00.598891+00:00",
"generatedAt": "2026-09-17T14:07:01.023314+00:00",
"lastSyncTime": "2026-09-17T14:07:00.815606+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2332,11 +2332,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"memory_capacity": 1,
"验证失败": 22
},
"failureCount": 71,
"failureCount": 72,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -2346,8 +2346,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 71,
"unresolvedFailureCount": 70
"total": 72,
"unresolvedFailureCount": 71
},
"Kunlunxin_p-800|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -2612,22 +2612,22 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 17,
"decisionTotal": 18,
"failureBreakdown": {
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 145,
"failureRate": 0.8951,
"failureRate": 0.8896,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 17,
"successRate": 0.1049,
"successCount": 18,
"successRate": 0.1104,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 162,
"total": 163,
"unresolvedFailureCount": 145
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -2811,11 +2811,11 @@
},
"unknown": {
"attributableFailureCount": 187,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 255,
"decisionFailureRate": 0.7305,
"decisionSuccessRate": 0.2695,
"decisionTotal": 256,
"failureBreakdown": {
"ambiguous_runtime": 162,
"ambiguous_runtime": 163,
"backend_operator": 4,
"framework_architecture_unsupported": 125,
"memory_capacity": 5,
@@ -2826,15 +2826,15 @@
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1096,
"failureRate": 0.9416,
"failureCount": 1097,
"failureRate": 0.9408,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 68,
"successRate": 0.0584,
"total": 1164,
"unresolvedFailureCount": 908
"successCount": 69,
"successRate": 0.0592,
"total": 1166,
"unresolvedFailureCount": 909
},
"vllm": {
"attributableFailureCount": 395,
@@ -2972,7 +2972,7 @@
"unresolvedFailureCount": 8
}
},
"generatedAt": "2026-09-17T13:48:00.831067+00:00",
"generatedAt": "2026-09-17T14:07:01.015379+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 56,
@@ -3169,20 +3169,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 107,
"ambiguous_runtime": 108,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 133,
"failureCount": 134,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 133,
"unresolvedFailureCount": 132
"total": 134,
"unresolvedFailureCount": 133
},
"MetaX_c-500": {
"attributableFailureCount": 62,
@@ -3263,9 +3263,9 @@
},
"Vastai_va16": {
"attributableFailureCount": 60,
"decisionFailureRate": 0.7792,
"decisionSuccessRate": 0.2208,
"decisionTotal": 77,
"decisionFailureRate": 0.7692,
"decisionSuccessRate": 0.2308,
"decisionTotal": 78,
"failureBreakdown": {
"ambiguous_runtime": 71,
"framework_architecture_unsupported": 53,
@@ -3275,13 +3275,13 @@
"验证失败": 130
},
"failureCount": 276,
"failureRate": 0.942,
"failureRate": 0.9388,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 17,
"successRate": 0.058,
"total": 293,
"successCount": 18,
"successRate": 0.0612,
"total": 294,
"unresolvedFailureCount": 216
},
"hygon_k100-ai": {
@@ -7298,13 +7298,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 16
"ambiguous_runtime": 17
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T13:39:06.611611+00:00",
"lastTerminalAt": "2026-09-17T14:07:00.815583+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7312,8 +7312,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 16
"total": 17,
"unresolvedFailureCount": 17
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -7473,18 +7473,18 @@
"unresolvedFailureCount": 2
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"decisionTotal": 11,
"failureBreakdown": {
"framework_architecture_unsupported": 5,
"platform_infrastructure": 4,
"tokenizer_compatibility": 7
"tokenizer_compatibility": 6
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
@@ -7496,25 +7496,25 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 7,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 3,
"memory_capacity": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"tokenizer_compatibility": 2,
"参数/模板问题": 1
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
@@ -7526,7 +7526,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 10,
"total": 9,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|text-generation": {
@@ -7535,23 +7535,23 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"参数/模板问题": 2
},
"failureCount": 2,
"failureRate": 0.3333,
"failureRate": 0.2857,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T22:43:36.337604+00:00",
"lastTerminalAt": "2026-09-17T14:07:00.815606+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.6667,
"successCount": 5,
"successRate": 0.7143,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
@@ -13042,15 +13042,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2135,
"totalRecords": 2238,
"terminalRecords": 2137,
"totalRecords": 2240,
"totals": {
"attributableFailureCount": 702,
"decisionFailureRate": 0.883,
"decisionSuccessRate": 0.117,
"decisionTotal": 795,
"decisionFailureRate": 0.8819,
"decisionSuccessRate": 0.1181,
"decisionTotal": 796,
"failureBreakdown": {
"ambiguous_runtime": 524,
"ambiguous_runtime": 525,
"backend_operator": 50,
"framework_architecture_unsupported": 467,
"memory_capacity": 12,
@@ -13062,28 +13062,28 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2042,
"failureRate": 0.9564,
"failureCount": 2043,
"failureRate": 0.956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 93,
"successRate": 0.0436,
"total": 2135,
"unresolvedFailureCount": 1330
"successCount": 94,
"successRate": 0.044,
"total": 2137,
"unresolvedFailureCount": 1331
},
"warnings": [
"GPU Mthreads_s4000 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 Sunrise_pt-200-x1 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 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 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 Ascend_910-b4|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。",
@@ -13110,6 +13110,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2238,
"summarizedRecords": 2240,
"version": 1
}