state: generation 8273 (cycle)

This commit is contained in:
2026-09-16 16:10:08 +00:00
parent 1d13a3f82b
commit d7e9bff5e8
9 changed files with 2134 additions and 2110 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T15:59:27.850405+00:00",
"lastSyncTime": "2026-09-16T15:59:25.244426+00:00",
"generatedAt": "2026-09-16T16:08:21.811082+00:00",
"lastSyncTime": "2026-09-16T16:08:21.748785+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1726,21 +1726,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"参数/模板问题": 9,
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 35,
"failureRate": 0.9459,
"failureCount": 36,
"failureRate": 0.9474,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0541,
"successRate": 0.0526,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 37,
"unresolvedFailureCount": 35
"total": 38,
"unresolvedFailureCount": 36
},
"Ascend_910-b3|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -1836,21 +1836,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"参数/模板问题": 12,
"参数/模板问题": 13,
"验证失败": 175
},
"failureCount": 187,
"failureRate": 0.9894,
"failureCount": 188,
"failureRate": 0.9895,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0106,
"successRate": 0.0105,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 189,
"unresolvedFailureCount": 187
"total": 190,
"unresolvedFailureCount": 188
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 1,
@@ -2349,21 +2349,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 9,
"failureBreakdown": {
"参数/模板问题": 9,
"参数/模板问题": 10,
"验证失败": 48
},
"failureCount": 57,
"failureRate": 0.8636,
"failureCount": 58,
"failureRate": 0.8657,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.1364,
"successRate": 0.1343,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 66,
"unresolvedFailureCount": 57
"total": 67,
"unresolvedFailureCount": 58
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 58,
@@ -2419,21 +2419,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"参数/模板问题": 7,
"参数/模板问题": 8,
"验证失败": 25
},
"failureCount": 32,
"failureRate": 0.9412,
"failureCount": 33,
"failureRate": 0.9429,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0588,
"successRate": 0.0571,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 32
"total": 35,
"unresolvedFailureCount": 33
},
"Mthreads_s4000|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -2491,21 +2491,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 2,
"参数/模板问题": 3,
"验证失败": 32
},
"failureCount": 34,
"failureRate": 0.9714,
"failureCount": 35,
"failureRate": 0.9722,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0286,
"successRate": 0.0278,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 35,
"unresolvedFailureCount": 34
"total": 36,
"unresolvedFailureCount": 35
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 54,
@@ -2565,21 +2565,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 14,
"failureBreakdown": {
"参数/模板问题": 14,
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 144,
"failureRate": 0.9114,
"failureCount": 145,
"failureRate": 0.9119,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0886,
"successRate": 0.0881,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 158,
"unresolvedFailureCount": 144
"total": 159,
"unresolvedFailureCount": 145
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 3,
@@ -2655,10 +2655,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1,
"参数/模板问题": 2,
"验证失败": 27
},
"failureCount": 28,
"failureCount": 29,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -2668,8 +2668,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 28,
"unresolvedFailureCount": 28
"total": 29,
"unresolvedFailureCount": 29
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 6,
@@ -2772,18 +2772,18 @@
"model_load": 46,
"platform_infrastructure": 1,
"tokenizer_compatibility": 5,
"参数/模板问题": 66,
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1079,
"failureRate": 0.9465,
"failureCount": 1086,
"failureRate": 0.9468,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 61,
"successRate": 0.0535,
"total": 1140,
"unresolvedFailureCount": 896
"successRate": 0.0532,
"total": 1147,
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 366,
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T15:59:27.843862+00:00",
"generatedAt": "2026-09-16T16:08:21.805748+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2932,18 +2932,18 @@
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 9,
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 120,
"failureRate": 0.9836,
"failureCount": 121,
"failureRate": 0.9837,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0164,
"total": 122,
"unresolvedFailureCount": 71
"successRate": 0.0163,
"total": 123,
"unresolvedFailureCount": 72
},
"Ascend_910-b4": {
"attributableFailureCount": 57,
@@ -2957,18 +2957,18 @@
"model_load": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 12,
"参数/模板问题": 13,
"验证失败": 175
},
"failureCount": 287,
"failureCount": 288,
"failureRate": 0.9931,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0069,
"total": 289,
"unresolvedFailureCount": 230
"total": 290,
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 49,
@@ -3143,18 +3143,18 @@
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 18,
"参数/模板问题": 19,
"验证失败": 48
},
"failureCount": 135,
"failureRate": 0.8824,
"failureCount": 136,
"failureRate": 0.8831,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.1176,
"total": 153,
"unresolvedFailureCount": 77
"successRate": 0.1169,
"total": 154,
"unresolvedFailureCount": 78
},
"Mthreads_s4000": {
"attributableFailureCount": 42,
@@ -3170,18 +3170,18 @@
"repository_structure": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 10,
"参数/模板问题": 11,
"验证失败": 26
},
"failureCount": 120,
"failureRate": 0.9449,
"failureCount": 121,
"failureRate": 0.9453,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.0551,
"total": 127,
"unresolvedFailureCount": 78
"successRate": 0.0547,
"total": 128,
"unresolvedFailureCount": 79
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 66,
@@ -3195,18 +3195,18 @@
"memory_capacity": 1,
"platform_infrastructure": 9,
"tokenizer_compatibility": 50,
"参数/模板问题": 17,
"参数/模板问题": 18,
"验证失败": 32
},
"failureCount": 125,
"failureCount": 126,
"failureRate": 0.9921,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 9,
"successCount": 1,
"successRate": 0.0079,
"total": 126,
"unresolvedFailureCount": 50
"total": 127,
"unresolvedFailureCount": 51
},
"Vastai_va16": {
"attributableFailureCount": 60,
@@ -3218,18 +3218,18 @@
"framework_architecture_unsupported": 53,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 14,
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 272,
"failureRate": 0.951,
"failureCount": 273,
"failureRate": 0.9512,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.049,
"total": 286,
"unresolvedFailureCount": 212
"successRate": 0.0488,
"total": 287,
"unresolvedFailureCount": 213
},
"hygon_k100-ai": {
"attributableFailureCount": 60,
@@ -3243,18 +3243,18 @@
"model_load": 5,
"repository_structure": 4,
"runtime_memory": 2,
"参数/模板问题": 9,
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 123,
"failureCount": 124,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 123,
"unresolvedFailureCount": 63
"total": 124,
"unresolvedFailureCount": 64
}
},
"observedGpuMemoryGiB": {
@@ -6128,22 +6128,22 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 1,
"failureRate": 0.5,
"failureCount": 2,
"failureRate": 0.6667,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T18:50:27.851864+00:00",
"lastTerminalAt": "2026-09-16T16:08:21.748752+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.5,
"successRate": 0.3333,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 4,
@@ -6205,13 +6205,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T23:52:34.207605+00:00",
"lastTerminalAt": "2026-09-16T16:08:21.748785+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6219,8 +6219,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 13,
@@ -6249,21 +6249,20 @@
"unresolvedFailureCount": 7
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 11,
"attributableFailureCount": 10,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 12,
"decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 1,
"framework_architecture_unsupported": 9,
"model_load": 1,
"参数/模板问题": 1
},
"failureCount": 17,
"failureRate": 0.9444,
"failureCount": 16,
"failureRate": 0.9412,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T09:03:21.744792+00:00",
@@ -6271,10 +6270,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0556,
"successRate": 0.0588,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 18,
"total": 17,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -6496,13 +6495,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T02:55:29.910734+00:00",
"lastTerminalAt": "2026-09-16T16:08:21.748761+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6510,8 +6509,8 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -6541,6 +6540,31 @@
"total": 8,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T16:08:21.748777+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
@@ -6576,13 +6600,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T02:55:29.910704+00:00",
"lastTerminalAt": "2026-09-16T16:08:21.748769+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6590,8 +6614,8 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 14,
@@ -6633,9 +6657,9 @@
"memory_capacity": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 4
"参数/模板问题": 1
},
"failureCount": 13,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
@@ -6647,8 +6671,8 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 4
"total": 10,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -6658,22 +6682,22 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 1,
"failureRate": 0.5,
"failureCount": 2,
"failureRate": 0.6667,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T22:59:41.110921+00:00",
"lastTerminalAt": "2026-09-16T16:08:21.748740+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.5,
"successRate": 0.3333,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 13,
@@ -6709,13 +6733,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
"参数/模板问题": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T07:43:04.407471+00:00",
"lastTerminalAt": "2026-09-16T16:08:21.748716+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6723,8 +6747,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 14,
@@ -10945,8 +10969,8 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2023,
"totalRecords": 2117,
"terminalRecords": 2030,
"totalRecords": 2124,
"totals": {
"attributableFailureCount": 652,
"decisionFailureRate": 0.8919,
@@ -10962,31 +10986,31 @@
"repository_structure": 8,
"runtime_memory": 15,
"tokenizer_compatibility": 60,
"参数/模板问题": 117,
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1944,
"failureRate": 0.9609,
"failureCount": 1951,
"failureRate": 0.9611,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 79,
"successRate": 0.0391,
"total": 2023,
"unresolvedFailureCount": 1282
"successRate": 0.0389,
"total": 2030,
"unresolvedFailureCount": 1289
},
"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 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 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 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 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。",
@@ -11012,6 +11036,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2117,
"summarizedRecords": 2124,
"version": 1
}