state: generation 10838 (intent)

This commit is contained in:
2026-09-20 19:48:06 +00:00
parent 8a28e6a870
commit b00a3175c5
8 changed files with 1870 additions and 1653 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T19:33:34.854966+00:00",
"lastSyncTime": "2026-09-20T19:33:34.552450+00:00",
"generatedAt": "2026-09-20T19:47:53.646354+00:00",
"lastSyncTime": "2026-09-20T19:47:52.978269+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2567,28 +2567,28 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 37,
"decisionFailureRate": 0.7115,
"decisionSuccessRate": 0.2885,
"decisionTotal": 52,
"attributableFailureCount": 38,
"decisionFailureRate": 0.717,
"decisionSuccessRate": 0.283,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 28,
"model_load": 8,
"model_load": 9,
"tokenizer_compatibility": 1
},
"failureCount": 40,
"failureRate": 0.7273,
"failureCount": 42,
"failureRate": 0.7368,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2727,
"successRate": 0.2632,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 55,
"unresolvedFailureCount": 3
"total": 57,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -4563,7 +4563,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 650,
"failureBreakdown": {
"ambiguous_runtime": 153,
"ambiguous_runtime": 154,
"architecture_compatibility": 30,
"attention_backend": 1,
"context_length": 42,
@@ -4575,7 +4575,7 @@
"runtime_memory": 53,
"tokenizer_compatibility": 79
},
"failureCount": 806,
"failureCount": 807,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -4585,8 +4585,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 806,
"unresolvedFailureCount": 153
"total": 807,
"unresolvedFailureCount": 154
},
"hygon_k100-ai|vllm|unknown": {
"attributableFailureCount": 1,
@@ -4709,34 +4709,34 @@
"unresolvedFailureCount": 6406
},
"vllm": {
"attributableFailureCount": 3491,
"attributableFailureCount": 3492,
"decisionFailureRate": 0.9771,
"decisionSuccessRate": 0.0229,
"decisionTotal": 3573,
"decisionTotal": 3574,
"failureBreakdown": {
"ambiguous_runtime": 1440,
"ambiguous_runtime": 1442,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1272,
"memory_capacity": 720,
"model_load": 200,
"model_load": 201,
"platform_infrastructure": 864,
"repository_structure": 470,
"runtime_memory": 62,
"tokenizer_compatibility": 409,
"参数/模板问题": 40
},
"failureCount": 5835,
"failureCount": 5838,
"failureRate": 0.9861,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 82,
"successRate": 0.0139,
"total": 5917,
"unresolvedFailureCount": 1480
"total": 5920,
"unresolvedFailureCount": 1482
},
"vllm-customized": {
"attributableFailureCount": 1,
@@ -4870,7 +4870,7 @@
"unresolvedFailureCount": 32
}
},
"generatedAt": "2026-09-20T19:33:34.846545+00:00",
"generatedAt": "2026-09-20T19:47:53.636798+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 78,
@@ -4926,17 +4926,17 @@
"unresolvedFailureCount": 591
},
"Biren_166m": {
"attributableFailureCount": 175,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 200,
"attributableFailureCount": 176,
"decisionFailureRate": 0.8756,
"decisionSuccessRate": 0.1244,
"decisionTotal": 201,
"failureBreakdown": {
"ambiguous_runtime": 133,
"ambiguous_runtime": 134,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 115,
"memory_capacity": 1,
"model_load": 19,
"model_load": 20,
"platform_infrastructure": 2,
"repository_structure": 18,
"runtime_memory": 2,
@@ -4945,15 +4945,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 613,
"failureRate": 0.9608,
"failureCount": 615,
"failureRate": 0.9609,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0392,
"total": 638,
"unresolvedFailureCount": 436
"successRate": 0.0391,
"total": 640,
"unresolvedFailureCount": 437
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 711,
@@ -5257,7 +5257,7 @@
"decisionSuccessRate": 0.0417,
"decisionTotal": 719,
"failureBreakdown": {
"ambiguous_runtime": 298,
"ambiguous_runtime": 299,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
@@ -5272,15 +5272,15 @@
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1460,
"failureCount": 1461,
"failureRate": 0.9799,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 30,
"successRate": 0.0201,
"total": 1490,
"unresolvedFailureCount": 767
"total": 1491,
"unresolvedFailureCount": 768
}
},
"observedGpuMemoryGiB": {
@@ -6244,6 +6244,29 @@
"total": 2,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|mpt|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "mpt",
"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|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6336,6 +6359,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -12195,6 +12241,29 @@
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
}
},
"recentCombinationStats": {
@@ -12382,31 +12451,31 @@
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 3,
"attributableFailureCount": 5,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 5,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 3,
"model_load": 1
"model_load": 2
},
"failureCount": 6,
"failureRate": 0.8571,
"failureCount": 8,
"failureRate": 0.8889,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T15:32:19.355892+00:00",
"lastTerminalAt": "2026-09-20T19:47:52.978269+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.1429,
"successRate": 0.1111,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 2
"total": 9,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -12654,9 +12723,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 7
},
"failureCount": 8,
"failureCount": 7,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -12668,8 +12737,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 7,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -13044,11 +13113,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 9,
"runtime_memory": 1
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -13060,8 +13129,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 6
"total": 15,
"unresolvedFailureCount": 5
}
},
"recentProfileCombinationStats": {
@@ -13391,6 +13460,31 @@
"total": 2,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|mpt|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T19:47:52.978254+00:00",
"modelType": "mpt",
"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|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -13416,6 +13510,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T19:47:52.978269+00:00",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -15367,6 +15486,31 @@
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T19:47:52.978239+00:00",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
}
},
"sizedProfileCombinationStats": {
@@ -16753,6 +16897,30 @@
"total": 2,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|mpt|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "mpt",
"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|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -16849,6 +17017,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen2|compressed-tensors|29": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 29,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|qwen2|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -25581,24 +25773,48 @@
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation|qwen3|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
}
},
"terminalRecords": 15939,
"totalRecords": 16073,
"terminalRecords": 15942,
"totalRecords": 16076,
"totals": {
"attributableFailureCount": 5788,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6719,
"attributableFailureCount": 5789,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6720,
"failureBreakdown": {
"ambiguous_runtime": 3796,
"ambiguous_runtime": 3798,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 2006,
"memory_capacity": 1196,
"model_load": 483,
"model_load": 484,
"platform_infrastructure": 922,
"repository_structure": 734,
"runtime_memory": 81,
@@ -25607,15 +25823,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15008,
"failureCount": 15011,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 931,
"successRate": 0.0584,
"total": 15939,
"unresolvedFailureCount": 8298
"total": 15942,
"unresolvedFailureCount": 8300
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -25660,12 +25876,12 @@
"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": 16073,
"summarizedRecords": 16076,
"version": 1
}