state: generation 5320 (cycle)

This commit is contained in:
2026-09-10 19:10:15 +00:00
parent dbd3b0beaa
commit bce7c2de35
9 changed files with 2159 additions and 2159 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T18:58:50.409136+00:00",
"lastSyncTime": "2026-09-10T18:58:50.012615+00:00",
"generatedAt": "2026-09-10T19:08:02.247819+00:00",
"lastSyncTime": "2026-09-10T19:08:02.004199+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1791,30 +1791,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 72,
"decisionFailureRate": 0.878,
"decisionSuccessRate": 0.122,
"decisionTotal": 82,
"attributableFailureCount": 73,
"decisionFailureRate": 0.8795,
"decisionSuccessRate": 0.1205,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 24,
"model_load": 25,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 139,
"failureRate": 0.9329,
"failureCount": 140,
"failureRate": 0.9333,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0671,
"successRate": 0.0667,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 149,
"total": 150,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2001,7 +2001,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2010,7 +2010,7 @@
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 68,
"failureCount": 69,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2020,8 +2020,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 68,
"unresolvedFailureCount": 36
"total": 69,
"unresolvedFailureCount": 37
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2292,29 +2292,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 126,
"decisionFailureRate": 0.7241,
"decisionSuccessRate": 0.2759,
"decisionTotal": 174,
"attributableFailureCount": 127,
"decisionFailureRate": 0.7257,
"decisionSuccessRate": 0.2743,
"decisionTotal": 175,
"failureBreakdown": {
"ambiguous_runtime": 123,
"backend_operator": 4,
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
"model_load": 26,
"model_load": 27,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 979,
"failureCount": 980,
"failureRate": 0.9533,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0467,
"total": 1027,
"total": 1028,
"unresolvedFailureCount": 852
},
"vllm": {
@@ -2323,7 +2323,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 183,
"ambiguous_runtime": 184,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2334,15 +2334,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 448,
"failureCount": 449,
"failureRate": 0.9956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0044,
"total": 450,
"unresolvedFailureCount": 207
"total": 451,
"unresolvedFailureCount": 208
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T18:58:50.404553+00:00",
"generatedAt": "2026-09-10T19:08:02.242490+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2608,27 +2608,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 72,
"decisionFailureRate": 0.878,
"decisionSuccessRate": 0.122,
"decisionTotal": 82,
"attributableFailureCount": 73,
"decisionFailureRate": 0.8795,
"decisionSuccessRate": 0.1205,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 24,
"model_load": 25,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 139,
"failureRate": 0.9329,
"failureCount": 140,
"failureRate": 0.9333,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0671,
"total": 149,
"successRate": 0.0667,
"total": 150,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -2682,7 +2682,7 @@
"decisionSuccessRate": 0.0571,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"backend_operator": 4,
"framework_architecture_unsupported": 22,
"memory_capacity": 1,
@@ -2692,15 +2692,15 @@
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 102,
"failureRate": 0.9808,
"failureCount": 103,
"failureRate": 0.981,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0192,
"total": 104,
"unresolvedFailureCount": 69
"successRate": 0.019,
"total": 105,
"unresolvedFailureCount": 70
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 36,
@@ -4172,11 +4172,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 12,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4188,8 +4188,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 8
"total": 10,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4271,22 +4271,22 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 1,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 9,
"model_load": 6,
"framework_architecture_unsupported": 8,
"model_load": 7,
"platform_infrastructure": 1
},
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T18:38:45.206121+00:00",
"lastTerminalAt": "2026-09-10T19:08:02.004176+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4406,16 +4406,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 14,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"runtime_memory": 1
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T18:58:50.012593+00:00",
"lastTerminalAt": "2026-09-10T19:08:02.004199+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4423,8 +4423,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 13
"total": 19,
"unresolvedFailureCount": 14
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4716,9 +4716,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 1
},
"failureCount": 3,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T16:13:44.313839+00:00",
@@ -4731,8 +4731,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
@@ -7073,19 +7073,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1622,
"totalRecords": 1709,
"terminalRecords": 1624,
"totalRecords": 1711,
"totals": {
"attributableFailureCount": 421,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 473,
"attributableFailureCount": 422,
"decisionFailureRate": 0.8903,
"decisionSuccessRate": 0.1097,
"decisionTotal": 474,
"failureBreakdown": {
"ambiguous_runtime": 374,
"ambiguous_runtime": 375,
"backend_operator": 40,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 48,
"model_load": 49,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -7093,30 +7093,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1570,
"failureRate": 0.9679,
"failureCount": 1572,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.0321,
"total": 1622,
"unresolvedFailureCount": 1145
"successRate": 0.032,
"total": 1624,
"unresolvedFailureCount": 1146
},
"warnings": [
"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 Iluvatar_mrv-100 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 Mthreads_s4000 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 MetaX_c-500 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 Biren_166m 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 Iluvatar_bi-150 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 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 Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|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 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 Cambricon_mlu-370-x8|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|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7131,11 +7132,10 @@
"组合 hygon_k100-ai|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|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|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-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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1709,
"summarizedRecords": 1711,
"version": 1
}