state: generation 10851 (cycle)

This commit is contained in:
2026-09-20 19:56:37 +00:00
parent 683f8f676b
commit 3c3f9ecadd
9 changed files with 1887 additions and 1817 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T19:49:27.002621+00:00",
"lastSyncTime": "2026-09-20T19:49:26.756443+00:00",
"generatedAt": "2026-09-20T19:56:30.417799+00:00",
"lastSyncTime": "2026-09-20T19:56:29.962443+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3096,18 +3096,18 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 19,
"attributableFailureCount": 20,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 19,
"decisionTotal": 20,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 6,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 6
"tokenizer_compatibility": 7
},
"failureCount": 26,
"failureCount": 27,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -3117,7 +3117,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 26,
"total": 27,
"unresolvedFailureCount": 7
},
"Iluvatar_bi-150|unknown|asr": {
@@ -4533,18 +4533,18 @@
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 24,
"attributableFailureCount": 25,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 24,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 14,
"model_load": 3,
"runtime_memory": 7,
"runtime_memory": 8,
"参数/模板问题": 8
},
"failureCount": 44,
"failureCount": 45,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -4554,7 +4554,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 44,
"total": 45,
"unresolvedFailureCount": 20
},
"hygon_k100-ai|vllm|text-generation": {
@@ -4656,25 +4656,25 @@
"unresolvedFailureCount": 114
},
"transformers": {
"attributableFailureCount": 20,
"attributableFailureCount": 21,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 20,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 42,
"framework_architecture_unsupported": 7,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 6
"tokenizer_compatibility": 7
},
"failureCount": 62,
"failureCount": 63,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 62,
"total": 63,
"unresolvedFailureCount": 42
},
"unknown": {
@@ -4779,25 +4779,25 @@
"unresolvedFailureCount": 48
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 24,
"attributableFailureCount": 25,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 24,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 14,
"model_load": 3,
"runtime_memory": 7,
"runtime_memory": 8,
"参数/模板问题": 8
},
"failureCount": 44,
"failureCount": 45,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 44,
"total": 45,
"unresolvedFailureCount": 20
},
"vllm_0_17_0_corex_4_4_0": {
@@ -4870,7 +4870,7 @@
"unresolvedFailureCount": 32
}
},
"generatedAt": "2026-09-20T19:49:26.994192+00:00",
"generatedAt": "2026-09-20T19:56:30.408875+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 78,
@@ -5032,10 +5032,10 @@
"unresolvedFailureCount": 551
},
"Iluvatar_bi-150": {
"attributableFailureCount": 735,
"decisionFailureRate": 0.8314,
"decisionSuccessRate": 0.1686,
"decisionTotal": 884,
"attributableFailureCount": 736,
"decisionFailureRate": 0.8316,
"decisionSuccessRate": 0.1684,
"decisionTotal": 885,
"failureBreakdown": {
"ambiguous_runtime": 614,
"architecture_compatibility": 15,
@@ -5047,19 +5047,19 @@
"platform_infrastructure": 21,
"repository_structure": 99,
"runtime_memory": 12,
"tokenizer_compatibility": 52,
"tokenizer_compatibility": 53,
"参数/模板问题": 319,
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1874,
"failureRate": 0.9263,
"failureCount": 1875,
"failureRate": 0.9264,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0737,
"total": 2023,
"successRate": 0.0736,
"total": 2024,
"unresolvedFailureCount": 1118
},
"Iluvatar_mrv-100": {
@@ -5252,10 +5252,10 @@
"unresolvedFailureCount": 1303
},
"hygon_k100-ai": {
"attributableFailureCount": 689,
"attributableFailureCount": 690,
"decisionFailureRate": 0.9583,
"decisionSuccessRate": 0.0417,
"decisionTotal": 719,
"decisionTotal": 720,
"failureBreakdown": {
"ambiguous_runtime": 299,
"architecture_compatibility": 32,
@@ -5266,20 +5266,20 @@
"model_load": 59,
"platform_infrastructure": 4,
"repository_structure": 116,
"runtime_memory": 60,
"runtime_memory": 61,
"tokenizer_compatibility": 79,
"参数/模板问题": 376,
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1461,
"failureCount": 1462,
"failureRate": 0.9799,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 30,
"successRate": 0.0201,
"total": 1491,
"total": 1492,
"unresolvedFailureCount": 768
}
},
@@ -7922,14 +7922,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "qwen3_5_moe",
@@ -7941,7 +7941,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": {
@@ -12080,6 +12080,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -12501,18 +12524,18 @@
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.7778,
"decisionSuccessRate": 0.2222,
"decisionTotal": 9,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 7
"framework_architecture_unsupported": 6
},
"failureCount": 10,
"failureRate": 0.8333,
"failureCount": 9,
"failureRate": 0.8182,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
@@ -12520,10 +12543,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1667,
"successRate": 0.1818,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 12,
"total": 11,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -12587,14 +12610,14 @@
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 5,
"memory_capacity": 5,
"tokenizer_compatibility": 6
"memory_capacity": 4,
"tokenizer_compatibility": 7
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T17:24:32.660503+00:00",
"lastTerminalAt": "2026-09-20T19:56:29.962428+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -12712,19 +12735,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 11,
"attributableFailureCount": 10,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6471,
"decisionSuccessRate": 0.3529,
"decisionTotal": 17,
"decisionFailureRate": 0.625,
"decisionSuccessRate": 0.375,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 10,
"tokenizer_compatibility": 1
"framework_architecture_unsupported": 10
},
"failureCount": 12,
"failureRate": 0.6667,
"failureCount": 11,
"failureRate": 0.6471,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
@@ -12732,10 +12754,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.3333,
"successRate": 0.3529,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 18,
"total": 17,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -13103,17 +13125,18 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"model_load": 2
"model_load": 2,
"runtime_memory": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null,
@@ -13125,7 +13148,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
@@ -14108,18 +14131,18 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-20T17:24:32.660503+00:00",
"lastTerminalAt": "2026-09-20T19:56:29.962428+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -14129,7 +14152,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": {
@@ -15510,6 +15533,31 @@
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-09-20T19:56:29.962443+00:00",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -19285,14 +19333,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none|33": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 33,
@@ -19305,7 +19353,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3|33": {
@@ -25581,6 +25629,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -25871,13 +25943,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 15943,
"totalRecords": 16077,
"terminalRecords": 15945,
"totalRecords": 16079,
"totals": {
"attributableFailureCount": 5789,
"attributableFailureCount": 5791,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6720,
"decisionTotal": 6722,
"failureBreakdown": {
"ambiguous_runtime": 3799,
"architecture_compatibility": 212,
@@ -25889,20 +25961,20 @@
"model_load": 484,
"platform_infrastructure": 922,
"repository_structure": 734,
"runtime_memory": 81,
"tokenizer_compatibility": 655,
"runtime_memory": 82,
"tokenizer_compatibility": 656,
"参数/模板问题": 3110,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15012,
"failureCount": 15014,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 931,
"successRate": 0.0584,
"total": 15943,
"total": 15945,
"unresolvedFailureCount": 8301
},
"warnings": [
@@ -25948,12 +26020,12 @@
"组合 Cambricon_mlu-370-x4|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 Ascend_910-b4|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 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 Cambricon_mlu-370-x8|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-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 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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16077,
"summarizedRecords": 16079,
"version": 1
}