state: generation 21389 (cycle)

This commit is contained in:
2026-10-06 10:16:29 +00:00
parent c0520891c3
commit cca853cd8f
8 changed files with 2031 additions and 1985 deletions

View File

@@ -2815,7 +2815,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-06T09:47:55.256039+00:00",
"generatedAt": "2026-10-06T10:16:23.066559+00:00",
"summary": {
"activeBlockCount": 142,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-06T10:11:20.847113+00:00",
"generatedAt": "2026-10-06T10:16:23.142341+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-06T10:11:20.847113+00:00",
"catalogUpdatedAt": "2026-10-06T10:16:23.142341+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-06T10:14:55.889012+00:00",
"generatedAt": "2026-10-06T10:16:23.142341+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6553,6 +6553,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-06T10:11:20.847113+00:00",
"taskTreeUpdatedAt": "2026-10-06T10:16:23.142341+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-06T09:15:34.201863+00:00",
"lastSyncTime": "2026-10-06T09:15:33.969896+00:00",
"generatedAt": "2026-10-06T10:16:22.973460+00:00",
"lastSyncTime": "2026-10-06T10:16:22.659565+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3525,24 +3525,24 @@
"decisionSuccessRate": 0.4194,
"decisionTotal": 31,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 54,
"framework_architecture_unsupported": 14,
"model_load": 3,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 74,
"failureRate": 0.8506,
"failureCount": 75,
"failureRate": 0.8523,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1494,
"successRate": 0.1477,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 87,
"unresolvedFailureCount": 56
"total": 88,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 22,
@@ -5151,27 +5151,27 @@
"unresolvedFailureCount": 3
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 40,
"attributableFailureCount": 36,
"decisionFailureRate": 0.878,
"decisionSuccessRate": 0.122,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 26,
"framework_architecture_unsupported": 23,
"framework_architecture_unsupported": 24,
"model_load": 12,
"参数/模板问题": 4
},
"failureCount": 65,
"failureRate": 0.9286,
"failureCount": 66,
"failureRate": 0.9296,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.0714,
"successRate": 0.0704,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 70,
"total": 71,
"unresolvedFailureCount": 30
},
"Vastai_va16|vllm|text-generation": {
@@ -5575,7 +5575,7 @@
"decisionSuccessRate": 0.3333,
"decisionTotal": 66,
"failureBreakdown": {
"ambiguous_runtime": 101,
"ambiguous_runtime": 102,
"framework_architecture_unsupported": 36,
"model_load": 7,
"platform_infrastructure": 1,
@@ -5583,15 +5583,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 153,
"failureRate": 0.8743,
"failureCount": 154,
"failureRate": 0.875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1257,
"total": 175,
"unresolvedFailureCount": 108
"successRate": 0.125,
"total": 176,
"unresolvedFailureCount": 109
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 61,
@@ -5641,28 +5641,28 @@
"unresolvedFailureCount": 34
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 171,
"decisionFailureRate": 0.9716,
"decisionSuccessRate": 0.0284,
"decisionTotal": 176,
"attributableFailureCount": 172,
"decisionFailureRate": 0.9718,
"decisionSuccessRate": 0.0282,
"decisionTotal": 177,
"failureBreakdown": {
"ambiguous_runtime": 355,
"backend_operator": 9,
"framework_architecture_unsupported": 46,
"framework_architecture_unsupported": 47,
"memory_capacity": 10,
"model_load": 12,
"platform_infrastructure": 25,
"tokenizer_compatibility": 94,
"参数/模板问题": 13
},
"failureCount": 564,
"failureCount": 565,
"failureRate": 0.9912,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0088,
"total": 569,
"total": 570,
"unresolvedFailureCount": 368
},
"vllm_tokenizer_patch": {
@@ -5694,7 +5694,7 @@
"unresolvedFailureCount": 233
}
},
"generatedAt": "2026-10-06T09:15:34.186944+00:00",
"generatedAt": "2026-10-06T10:16:22.954602+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5816,7 +5816,7 @@
"decisionSuccessRate": 0.1899,
"decisionTotal": 79,
"failureBreakdown": {
"ambiguous_runtime": 157,
"ambiguous_runtime": 158,
"framework_architecture_unsupported": 51,
"memory_capacity": 4,
"model_load": 6,
@@ -5825,15 +5825,15 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 286,
"failureRate": 0.9502,
"failureCount": 287,
"failureRate": 0.9503,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0498,
"total": 301,
"unresolvedFailureCount": 220
"successRate": 0.0497,
"total": 302,
"unresolvedFailureCount": 221
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -6059,14 +6059,14 @@
"unresolvedFailureCount": 422
},
"Vastai_va16": {
"attributableFailureCount": 467,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 524,
"attributableFailureCount": 468,
"decisionFailureRate": 0.8914,
"decisionSuccessRate": 0.1086,
"decisionTotal": 525,
"failureBreakdown": {
"ambiguous_runtime": 826,
"context_length": 9,
"framework_architecture_unsupported": 202,
"framework_architecture_unsupported": 203,
"memory_capacity": 133,
"model_load": 54,
"platform_infrastructure": 14,
@@ -6076,14 +6076,14 @@
"日志缺失": 124,
"验证失败": 130
},
"failureCount": 1803,
"failureCount": 1804,
"failureRate": 0.9694,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 57,
"successRate": 0.0306,
"total": 1860,
"total": 1861,
"unresolvedFailureCount": 1322
},
"hygon_k100-ai": {
@@ -13113,9 +13113,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "lfm2",
@@ -13127,8 +13127,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -23337,14 +23337,14 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
@@ -23356,7 +23356,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|torchao": {
@@ -39955,6 +39955,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 30,
"modelType": "lfm2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -55178,6 +55202,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none|31": {
"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": 31,
"modelType": "spark2_5",
"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|spark2_5|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -57345,20 +57393,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17331,
"totalRecords": 17555,
"terminalRecords": 17333,
"totalRecords": 17557,
"totals": {
"attributableFailureCount": 6231,
"decisionFailureRate": 0.8643,
"decisionSuccessRate": 0.1357,
"decisionTotal": 7209,
"attributableFailureCount": 6232,
"decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356,
"decisionTotal": 7210,
"failureBreakdown": {
"ambiguous_runtime": 4543,
"ambiguous_runtime": 4544,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
"context_length": 327,
"framework_architecture_unsupported": 2257,
"framework_architecture_unsupported": 2258,
"memory_capacity": 1206,
"model_load": 566,
"platform_infrastructure": 951,
@@ -57369,15 +57417,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16353,
"failureCount": 16355,
"failureRate": 0.9436,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 951,
"successCount": 978,
"successRate": 0.0564,
"total": 17331,
"unresolvedFailureCount": 9171
"total": 17333,
"unresolvedFailureCount": 9172
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -57386,14 +57434,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 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 Mthreads_s4000 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 Cambricon_mlu-370-x8 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-b4 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-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 Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"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 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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -57437,6 +57485,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17555,
"summarizedRecords": 17557,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff