state: generation 19400 (cycle)

This commit is contained in:
2026-10-01 22:07:12 +00:00
parent 06ec2747ee
commit 74e6d620b7
9 changed files with 1357 additions and 1336 deletions

View File

@@ -3341,7 +3341,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-01T21:56:07.948433+00:00",
"generatedAt": "2026-10-01T22:04:49.197255+00:00",
"summary": {
"activeBlockCount": 168,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-01T22:03:43.054869+00:00",
"generatedAt": "2026-10-01T22:06:46.367346+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-01T22:03:43.054869+00:00",
"catalogUpdatedAt": "2026-10-01T22:06:46.367346+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-01T22:03:43.054869+00:00",
"generatedAt": "2026-10-01T22:06:46.367346+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6630,6 +6630,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-01T22:03:43.054869+00:00",
"taskTreeUpdatedAt": "2026-10-01T22:06:46.367346+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-01T20:57:12.703376+00:00",
"lastSyncTime": "2026-10-01T20:57:12.462569+00:00",
"generatedAt": "2026-10-01T22:04:49.108094+00:00",
"lastSyncTime": "2026-10-01T22:04:48.852822+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3922,29 +3922,29 @@
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 20,
"decisionFailureRate": 0.6897,
"decisionSuccessRate": 0.3103,
"decisionTotal": 29,
"attributableFailureCount": 21,
"decisionFailureRate": 0.7,
"decisionSuccessRate": 0.3,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 45,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"model_load": 3,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 70,
"failureRate": 0.8861,
"failureCount": 71,
"failureRate": 0.8875,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 9,
"successRate": 0.1139,
"successRate": 0.1125,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 79,
"total": 80,
"unresolvedFailureCount": 49
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -6093,27 +6093,27 @@
"unresolvedFailureCount": 51
},
"vllm-mlu": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.614,
"decisionSuccessRate": 0.386,
"decisionTotal": 57,
"attributableFailureCount": 36,
"decisionFailureRate": 0.6207,
"decisionSuccessRate": 0.3793,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 95,
"framework_architecture_unsupported": 29,
"framework_architecture_unsupported": 30,
"model_load": 5,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 138,
"failureRate": 0.8625,
"failureCount": 139,
"failureRate": 0.8634,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1375,
"total": 160,
"successRate": 0.1366,
"total": 161,
"unresolvedFailureCount": 102
},
"vllm-patch-tokenizer": {
@@ -6217,7 +6217,7 @@
"unresolvedFailureCount": 225
}
},
"generatedAt": "2026-10-01T20:57:12.690281+00:00",
"generatedAt": "2026-10-01T22:04:49.095265+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 113,
@@ -6305,15 +6305,15 @@
"unresolvedFailureCount": 564
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 753,
"decisionFailureRate": 0.9105,
"decisionSuccessRate": 0.0895,
"decisionTotal": 827,
"attributableFailureCount": 754,
"decisionFailureRate": 0.9106,
"decisionSuccessRate": 0.0894,
"decisionTotal": 828,
"failureBreakdown": {
"ambiguous_runtime": 510,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 306,
"framework_architecture_unsupported": 307,
"memory_capacity": 219,
"model_load": 7,
"platform_infrastructure": 16,
@@ -6323,14 +6323,14 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1621,
"failureRate": 0.9563,
"failureCount": 1622,
"failureRate": 0.9564,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 74,
"successRate": 0.0437,
"total": 1695,
"successRate": 0.0436,
"total": 1696,
"unresolvedFailureCount": 852
},
"Cambricon_mlu-370-x8": {
@@ -11511,15 +11511,15 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 5,
"验证失败": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
@@ -11531,7 +11531,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors": {
@@ -35772,6 +35772,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -54498,20 +54522,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17209,
"totalRecords": 17430,
"terminalRecords": 17210,
"totalRecords": 17431,
"totals": {
"attributableFailureCount": 6170,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7145,
"attributableFailureCount": 6171,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7146,
"failureBreakdown": {
"ambiguous_runtime": 4497,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"framework_architecture_unsupported": 2213,
"framework_architecture_unsupported": 2214,
"memory_capacity": 1206,
"model_load": 553,
"platform_infrastructure": 944,
@@ -54522,30 +54546,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16234,
"failureCount": 16235,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 944,
"successCount": 975,
"successRate": 0.0567,
"total": 17209,
"total": 17210,
"unresolvedFailureCount": 9120
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 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 hygon_k100-ai 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 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 Vastai_va16 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 Iluvatar_bi-150 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 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。",
"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 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。",
@@ -54590,6 +54614,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17430,
"summarizedRecords": 17431,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff