state: generation 11138 (cycle)

This commit is contained in:
2026-09-21 03:26:08 +00:00
parent 9299b7b94e
commit 1143b13293
9 changed files with 1850 additions and 1712 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T03:09:34.638519+00:00",
"lastSyncTime": "2026-09-21T03:09:34.579964+00:00",
"generatedAt": "2026-09-21T03:25:55.875915+00:00",
"lastSyncTime": "2026-09-21T03:25:53.878060+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1165,7 +1165,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-20T18:51:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T18:51:21+00:00",
@@ -1173,12 +1173,10 @@
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo"
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired"
],
"sourceTaskIds": [
"4523697",
"4490374"
"4523697"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -2741,10 +2739,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 26,
"ambiguous_runtime": 27,
"framework_architecture_unsupported": 18
},
"failureCount": 44,
"failureCount": 45,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -2754,8 +2752,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 44,
"unresolvedFailureCount": 26
"total": 45,
"unresolvedFailureCount": 27
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 199,
@@ -4406,7 +4404,7 @@
"decisionSuccessRate": 0.2299,
"decisionTotal": 87,
"failureBreakdown": {
"ambiguous_runtime": 59,
"ambiguous_runtime": 60,
"backend_operator": 8,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
@@ -4416,18 +4414,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 12
},
"failureCount": 138,
"failureRate": 0.8734,
"failureCount": 139,
"failureRate": 0.8742,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.1266,
"successRate": 0.1258,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 158,
"unresolvedFailureCount": 71
"total": 159,
"unresolvedFailureCount": 72
},
"Mthreads_s4000|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
@@ -5053,7 +5051,7 @@
"decisionSuccessRate": 0.0231,
"decisionTotal": 3589,
"failureBreakdown": {
"ambiguous_runtime": 1460,
"ambiguous_runtime": 1461,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5067,15 +5065,15 @@
"tokenizer_compatibility": 410,
"参数/模板问题": 41
},
"failureCount": 5871,
"failureCount": 5872,
"failureRate": 0.9861,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 83,
"successRate": 0.0139,
"total": 5954,
"unresolvedFailureCount": 1501
"total": 5955,
"unresolvedFailureCount": 1502
},
"vllm-customized": {
"attributableFailureCount": 2,
@@ -5195,25 +5193,25 @@
"decisionSuccessRate": 0.037,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 39,
"ambiguous_runtime": 40,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 19
},
"failureCount": 110,
"failureRate": 0.9821,
"failureCount": 111,
"failureRate": 0.9823,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0179,
"total": 112,
"unresolvedFailureCount": 58
"successRate": 0.0177,
"total": 113,
"unresolvedFailureCount": 59
}
},
"generatedAt": "2026-09-21T03:09:34.628728+00:00",
"generatedAt": "2026-09-21T03:25:55.865318+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 90,
@@ -5246,7 +5244,7 @@
"decisionSuccessRate": 0.1662,
"decisionTotal": 373,
"failureBreakdown": {
"ambiguous_runtime": 158,
"ambiguous_runtime": 159,
"context_length": 1,
"framework_architecture_unsupported": 171,
"memory_capacity": 18,
@@ -5258,15 +5256,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 913,
"failureRate": 0.9364,
"failureCount": 914,
"failureRate": 0.9365,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 62,
"successRate": 0.0636,
"total": 975,
"unresolvedFailureCount": 601
"successRate": 0.0635,
"total": 976,
"unresolvedFailureCount": 602
},
"Biren_166m": {
"attributableFailureCount": 180,
@@ -5515,7 +5513,7 @@
"decisionSuccessRate": 0.3604,
"decisionTotal": 111,
"failureBreakdown": {
"ambiguous_runtime": 105,
"ambiguous_runtime": 106,
"backend_operator": 8,
"framework_architecture_unsupported": 50,
"memory_capacity": 1,
@@ -5527,15 +5525,15 @@
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 354,
"failureRate": 0.8985,
"failureCount": 355,
"failureRate": 0.8987,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 40,
"successRate": 0.1015,
"total": 394,
"unresolvedFailureCount": 283
"successRate": 0.1013,
"total": 395,
"unresolvedFailureCount": 284
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
@@ -6494,6 +6492,29 @@
"total": 6,
"unresolvedFailureCount": 6
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12379,6 +12400,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|gemma4|none": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -13803,10 +13847,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 6
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -13818,8 +13862,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 9
"total": 16,
"unresolvedFailureCount": 10
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 0,
@@ -13847,17 +13891,17 @@
"unresolvedFailureCount": 4
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 3,
"model_load": 1
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -13869,7 +13913,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 5,
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation": {
@@ -14402,12 +14446,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"backend_operator": 2,
"framework_architecture_unsupported": 4,
"runtime_memory": 1
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -14419,8 +14463,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 2
"total": 10,
"unresolvedFailureCount": 3
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -14621,19 +14665,19 @@
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 3,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -14645,7 +14689,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 9,
"total": 8,
"unresolvedFailureCount": 3
}
},
@@ -15225,6 +15269,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T03:25:53.878029+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -18055,6 +18124,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma2|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": "2026-09-21T03:25:53.878060+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19519,6 +19613,30 @@
"total": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -28114,6 +28232,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|gemma2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|gemma4|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -30046,15 +30188,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16064,
"totalRecords": 16237,
"terminalRecords": 16066,
"totalRecords": 16239,
"totals": {
"attributableFailureCount": 5833,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6770,
"failureBreakdown": {
"ambiguous_runtime": 3839,
"ambiguous_runtime": 3841,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -30070,31 +30212,31 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15127,
"failureCount": 15129,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 937,
"successRate": 0.0583,
"total": 16064,
"unresolvedFailureCount": 8372
"total": 16066,
"unresolvedFailureCount": 8374
},
"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。",
@@ -30131,6 +30273,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16237,
"summarizedRecords": 16239,
"version": 1
}