state: generation 11468 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T12:58:51.737494+00:00",
|
||||
"lastSyncTime": "2026-09-21T12:58:50.741637+00:00",
|
||||
"generatedAt": "2026-09-21T13:03:44.822858+00:00",
|
||||
"lastSyncTime": "2026-09-21T13:03:44.265526+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4954,27 +4954,27 @@
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 13,
|
||||
"decisionFailureRate": 0.7222,
|
||||
"decisionSuccessRate": 0.2778,
|
||||
"decisionTotal": 18,
|
||||
"attributableFailureCount": 14,
|
||||
"decisionFailureRate": 0.7368,
|
||||
"decisionSuccessRate": 0.2632,
|
||||
"decisionTotal": 19,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 14,
|
||||
"framework_architecture_unsupported": 11,
|
||||
"model_load": 2,
|
||||
"model_load": 3,
|
||||
"参数/模板问题": 4
|
||||
},
|
||||
"failureCount": 31,
|
||||
"failureRate": 0.8611,
|
||||
"failureCount": 32,
|
||||
"failureRate": 0.8649,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 5,
|
||||
"successRate": 0.1389,
|
||||
"successRate": 0.1351,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 36,
|
||||
"total": 37,
|
||||
"unresolvedFailureCount": 18
|
||||
},
|
||||
"Vastai_va16|vllm|text-generation": {
|
||||
@@ -5440,28 +5440,28 @@
|
||||
"unresolvedFailureCount": 23
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 122,
|
||||
"decisionFailureRate": 0.9606,
|
||||
"decisionSuccessRate": 0.0394,
|
||||
"decisionTotal": 127,
|
||||
"attributableFailureCount": 123,
|
||||
"decisionFailureRate": 0.9609,
|
||||
"decisionSuccessRate": 0.0391,
|
||||
"decisionTotal": 128,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 166,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 7,
|
||||
"model_load": 2,
|
||||
"model_load": 3,
|
||||
"platform_infrastructure": 17,
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 318,
|
||||
"failureRate": 0.9845,
|
||||
"failureCount": 319,
|
||||
"failureRate": 0.9846,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 17,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0155,
|
||||
"total": 323,
|
||||
"successRate": 0.0154,
|
||||
"total": 324,
|
||||
"unresolvedFailureCount": 179
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -5492,7 +5492,7 @@
|
||||
"unresolvedFailureCount": 87
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T12:58:51.725574+00:00",
|
||||
"generatedAt": "2026-09-21T13:03:44.812305+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 94,
|
||||
@@ -5848,16 +5848,16 @@
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"attributableFailureCount": 445,
|
||||
"decisionFailureRate": 0.8865,
|
||||
"decisionSuccessRate": 0.1135,
|
||||
"decisionTotal": 502,
|
||||
"attributableFailureCount": 446,
|
||||
"decisionFailureRate": 0.8867,
|
||||
"decisionSuccessRate": 0.1133,
|
||||
"decisionTotal": 503,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 814,
|
||||
"context_length": 9,
|
||||
"framework_architecture_unsupported": 190,
|
||||
"memory_capacity": 133,
|
||||
"model_load": 44,
|
||||
"model_load": 45,
|
||||
"platform_infrastructure": 14,
|
||||
"repository_structure": 57,
|
||||
"tokenizer_compatibility": 12,
|
||||
@@ -5865,14 +5865,14 @@
|
||||
"日志缺失": 124,
|
||||
"验证失败": 130
|
||||
},
|
||||
"failureCount": 1769,
|
||||
"failureCount": 1770,
|
||||
"failureRate": 0.9688,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 14,
|
||||
"successCount": 57,
|
||||
"successRate": 0.0312,
|
||||
"total": 1826,
|
||||
"total": 1827,
|
||||
"unresolvedFailureCount": 1310
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
@@ -15141,6 +15141,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -16033,10 +16056,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -16048,8 +16071,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -16703,16 +16726,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -16724,7 +16748,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|unknown|text-generation": {
|
||||
@@ -16808,31 +16832,6 @@
|
||||
}
|
||||
},
|
||||
"recentProfileCombinationStats": {
|
||||
"Ascend_910-b3|vllm|text-generation|mistral3|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": "2026-09-21T10:33:30.477588+00:00",
|
||||
"modelType": "mistral3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -20091,6 +20090,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-21T13:03:44.265526+00:00",
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -33609,6 +33633,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 29,
|
||||
"modelType": "lfm2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -34761,13 +34809,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16278,
|
||||
"totalRecords": 16462,
|
||||
"terminalRecords": 16279,
|
||||
"totalRecords": 16463,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5880,
|
||||
"attributableFailureCount": 5881,
|
||||
"decisionFailureRate": 0.8617,
|
||||
"decisionSuccessRate": 0.1383,
|
||||
"decisionTotal": 6824,
|
||||
"decisionTotal": 6825,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3948,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -34776,7 +34824,7 @@
|
||||
"context_length": 320,
|
||||
"framework_architecture_unsupported": 2069,
|
||||
"memory_capacity": 1197,
|
||||
"model_load": 497,
|
||||
"model_load": 498,
|
||||
"platform_infrastructure": 925,
|
||||
"repository_structure": 736,
|
||||
"runtime_memory": 85,
|
||||
@@ -34785,31 +34833,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15334,
|
||||
"failureCount": 15335,
|
||||
"failureRate": 0.942,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 944,
|
||||
"successRate": 0.058,
|
||||
"total": 16278,
|
||||
"total": 16279,
|
||||
"unresolvedFailureCount": 8529
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 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 Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-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-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 Cambricon_mlu-370-x4 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-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 Ascend_910-b4 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 Iluvatar_bi-150|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|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。",
|
||||
@@ -34849,6 +34897,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16462,
|
||||
"summarizedRecords": 16463,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user