state: generation 18313 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-29T07:59:04.015459+00:00",
|
||||
"lastSyncTime": "2026-09-29T07:59:03.756289+00:00",
|
||||
"generatedAt": "2026-09-29T08:08:03.066000+00:00",
|
||||
"lastSyncTime": "2026-09-29T08:08:02.743471+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -5422,18 +5422,18 @@
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 115,
|
||||
"attributableFailureCount": 116,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 115,
|
||||
"decisionTotal": 116,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"framework_architecture_unsupported": 16,
|
||||
"platform_infrastructure": 21,
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 142,
|
||||
"failureCount": 143,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -5443,14 +5443,14 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 142,
|
||||
"total": 143,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 616,
|
||||
"attributableFailureCount": 617,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 616,
|
||||
"decisionTotal": 617,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 109,
|
||||
"architecture_compatibility": 43,
|
||||
@@ -5458,23 +5458,23 @@
|
||||
"context_length": 34,
|
||||
"framework_architecture_unsupported": 143,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 207,
|
||||
"platform_infrastructure": 208,
|
||||
"repository_structure": 75,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 179,
|
||||
"tokenizer_compatibility": 180,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 941,
|
||||
"failureCount": 943,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 207,
|
||||
"platformFailureCount": 208,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 941,
|
||||
"total": 943,
|
||||
"unresolvedFailureCount": 118
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||
@@ -5976,10 +5976,10 @@
|
||||
"unresolvedFailureCount": 6473
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3629,
|
||||
"attributableFailureCount": 3630,
|
||||
"decisionFailureRate": 0.974,
|
||||
"decisionSuccessRate": 0.026,
|
||||
"decisionTotal": 3726,
|
||||
"decisionTotal": 3727,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1587,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -5989,20 +5989,20 @@
|
||||
"framework_architecture_unsupported": 1363,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 220,
|
||||
"platform_infrastructure": 871,
|
||||
"platform_infrastructure": 872,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 66,
|
||||
"tokenizer_compatibility": 416,
|
||||
"tokenizer_compatibility": 417,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6137,
|
||||
"failureCount": 6139,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 871,
|
||||
"platformFailureCount": 872,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6234,
|
||||
"total": 6236,
|
||||
"unresolvedFailureCount": 1637
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -6100,28 +6100,28 @@
|
||||
"unresolvedFailureCount": 26
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 153,
|
||||
"decisionFailureRate": 0.9684,
|
||||
"decisionSuccessRate": 0.0316,
|
||||
"decisionTotal": 158,
|
||||
"attributableFailureCount": 154,
|
||||
"decisionFailureRate": 0.9686,
|
||||
"decisionSuccessRate": 0.0314,
|
||||
"decisionTotal": 159,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 326,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 34,
|
||||
"framework_architecture_unsupported": 35,
|
||||
"memory_capacity": 10,
|
||||
"model_load": 9,
|
||||
"platform_infrastructure": 21,
|
||||
"tokenizer_compatibility": 91,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 513,
|
||||
"failureRate": 0.9903,
|
||||
"failureCount": 514,
|
||||
"failureRate": 0.9904,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 21,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0097,
|
||||
"total": 518,
|
||||
"successRate": 0.0096,
|
||||
"total": 519,
|
||||
"unresolvedFailureCount": 339
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -6153,7 +6153,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-29T07:59:04.002711+00:00",
|
||||
"generatedAt": "2026-09-29T08:08:03.050140+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6488,32 +6488,32 @@
|
||||
"unresolvedFailureCount": 299
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 750,
|
||||
"decisionFailureRate": 0.8897,
|
||||
"decisionSuccessRate": 0.1103,
|
||||
"decisionTotal": 843,
|
||||
"attributableFailureCount": 752,
|
||||
"decisionFailureRate": 0.8899,
|
||||
"decisionSuccessRate": 0.1101,
|
||||
"decisionTotal": 845,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
"backend_operator": 37,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 160,
|
||||
"framework_architecture_unsupported": 161,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 228,
|
||||
"platform_infrastructure": 229,
|
||||
"repository_structure": 83,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 273,
|
||||
"tokenizer_compatibility": 274,
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1400,
|
||||
"failureRate": 0.9377,
|
||||
"failureCount": 1403,
|
||||
"failureRate": 0.9378,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 228,
|
||||
"platformFailureCount": 229,
|
||||
"successCount": 93,
|
||||
"successRate": 0.0623,
|
||||
"total": 1493,
|
||||
"successRate": 0.0622,
|
||||
"total": 1496,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -20979,6 +20979,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -21187,6 +21210,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|gptq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"quantizationMethod": "gptq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -23746,7 +23792,7 @@
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 7,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -23756,11 +23802,11 @@
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 7,
|
||||
"successCount": 6,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -23790,6 +23836,31 @@
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-29T08:08:02.743424+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -49057,6 +49128,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none|27": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -49370,6 +49465,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|gptq|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"quantizationMethod": "gptq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -52210,38 +52329,38 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17096,
|
||||
"totalRecords": 17317,
|
||||
"terminalRecords": 17099,
|
||||
"totalRecords": 17320,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6128,
|
||||
"attributableFailureCount": 6130,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7096,
|
||||
"decisionTotal": 7098,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4438,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
"context_length": 322,
|
||||
"framework_architecture_unsupported": 2183,
|
||||
"framework_architecture_unsupported": 2184,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 550,
|
||||
"platform_infrastructure": 939,
|
||||
"platform_infrastructure": 940,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 101,
|
||||
"tokenizer_compatibility": 681,
|
||||
"tokenizer_compatibility": 682,
|
||||
"参数/模板问题": 3228,
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16128,
|
||||
"failureCount": 16131,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 939,
|
||||
"platformFailureCount": 940,
|
||||
"successCount": 968,
|
||||
"successRate": 0.0566,
|
||||
"total": 17096,
|
||||
"total": 17099,
|
||||
"unresolvedFailureCount": 9061
|
||||
},
|
||||
"warnings": [
|
||||
@@ -52271,6 +52390,7 @@
|
||||
"组合 Kunlunxin_p-800|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。",
|
||||
"组合 Ascend_910-b4|llamacpp|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_mrv-100|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 Kunlunxin_p-800|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 MetaX_c-500|vllm|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|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。",
|
||||
@@ -52295,11 +52415,10 @@
|
||||
"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 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 Ascend_910-b3|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。",
|
||||
"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 Kunlunxin_p-800|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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17317,
|
||||
"summarizedRecords": 17320,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user