state: generation 8270 (cycle)

This commit is contained in:
2026-09-16 16:01:14 +00:00
parent 04a5db0f14
commit c8798b7683
9 changed files with 2086 additions and 2042 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T14:22:24.640225+00:00",
"lastSyncTime": "2026-09-16T14:22:22.658468+00:00",
"generatedAt": "2026-09-16T15:59:27.850405+00:00",
"lastSyncTime": "2026-09-16T15:59:25.244426+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1928,25 +1928,25 @@
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 11,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 12,
"attributableFailureCount": 13,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 14,
"failureBreakdown": {
"framework_architecture_unsupported": 7,
"model_load": 4
"framework_architecture_unsupported": 8,
"model_load": 5
},
"failureCount": 11,
"failureRate": 0.9167,
"failureCount": 13,
"failureRate": 0.9286,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0833,
"successRate": 0.0714,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 12,
"total": 14,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2181,25 +2181,25 @@
"decisionSuccessRate": 0.1154,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"backend_operator": 4,
"framework_architecture_unsupported": 6,
"model_load": 4,
"runtime_memory": 9,
"参数/模板问题": 1
},
"failureCount": 34,
"failureRate": 0.9189,
"failureCount": 35,
"failureRate": 0.9211,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0811,
"successRate": 0.0789,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 37,
"unresolvedFailureCount": 11
"total": 38,
"unresolvedFailureCount": 12
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 26,
@@ -2786,30 +2786,30 @@
"unresolvedFailureCount": 896
},
"vllm": {
"attributableFailureCount": 364,
"decisionFailureRate": 0.9604,
"decisionSuccessRate": 0.0396,
"decisionTotal": 379,
"attributableFailureCount": 366,
"decisionFailureRate": 0.9606,
"decisionSuccessRate": 0.0394,
"decisionTotal": 381,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 269,
"framework_architecture_unsupported": 270,
"memory_capacity": 7,
"model_load": 30,
"model_load": 31,
"platform_infrastructure": 2,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 619,
"failureRate": 0.9763,
"failureCount": 621,
"failureRate": 0.9764,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0237,
"total": 634,
"successRate": 0.0236,
"total": 636,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2859,22 +2859,22 @@
"decisionSuccessRate": 0.1154,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"backend_operator": 4,
"framework_architecture_unsupported": 6,
"model_load": 4,
"runtime_memory": 9,
"参数/模板问题": 1
},
"failureCount": 34,
"failureRate": 0.9189,
"failureCount": 35,
"failureRate": 0.9211,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0811,
"total": 37,
"unresolvedFailureCount": 11
"successRate": 0.0789,
"total": 38,
"unresolvedFailureCount": 12
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 57,
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T14:22:24.635026+00:00",
"generatedAt": "2026-09-16T15:59:27.843862+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2971,28 +2971,28 @@
"unresolvedFailureCount": 230
},
"Biren_166m": {
"attributableFailureCount": 47,
"decisionFailureRate": 0.94,
"decisionSuccessRate": 0.06,
"decisionTotal": 50,
"attributableFailureCount": 49,
"decisionFailureRate": 0.9423,
"decisionSuccessRate": 0.0577,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 34,
"framework_architecture_unsupported": 35,
"memory_capacity": 1,
"model_load": 7,
"model_load": 8,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 106,
"failureRate": 0.9725,
"failureCount": 108,
"failureRate": 0.973,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0275,
"total": 109,
"successRate": 0.027,
"total": 111,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3066,7 +3066,7 @@
"decisionSuccessRate": 0.1525,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 19,
"backend_operator": 7,
"framework_architecture_unsupported": 20,
"model_load": 11,
@@ -3075,15 +3075,15 @@
"参数/模板问题": 3,
"验证失败": 30
},
"failureCount": 101,
"failureRate": 0.9182,
"failureCount": 102,
"failureRate": 0.9189,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0818,
"total": 110,
"unresolvedFailureCount": 51
"successRate": 0.0811,
"total": 111,
"unresolvedFailureCount": 52
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 111,
@@ -3436,14 +3436,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|awq": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"model_load": 3
"model_load": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -3455,7 +3455,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|nanbeige|compressed-tensors": {
@@ -3571,6 +3571,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4263,9 +4286,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5_moe",
@@ -4277,8 +4300,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -7002,14 +7025,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"model_load": 3
"model_load": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -7022,7 +7045,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|nanbeige|compressed-tensors|32": {
@@ -7167,6 +7190,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -8127,9 +8174,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
@@ -8142,8 +8189,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0,
@@ -10898,19 +10945,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2020,
"totalRecords": 2114,
"terminalRecords": 2023,
"totalRecords": 2117,
"totals": {
"attributableFailureCount": 650,
"decisionFailureRate": 0.8916,
"decisionSuccessRate": 0.1084,
"decisionTotal": 729,
"attributableFailureCount": 652,
"decisionFailureRate": 0.8919,
"decisionSuccessRate": 0.1081,
"decisionTotal": 731,
"failureBreakdown": {
"ambiguous_runtime": 491,
"ambiguous_runtime": 492,
"backend_operator": 45,
"framework_architecture_unsupported": 426,
"framework_architecture_unsupported": 427,
"memory_capacity": 12,
"model_load": 84,
"model_load": 85,
"platform_infrastructure": 10,
"repository_structure": 8,
"runtime_memory": 15,
@@ -10918,28 +10965,28 @@
"参数/模板问题": 117,
"验证失败": 673
},
"failureCount": 1941,
"failureCount": 1944,
"failureRate": 0.9609,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 79,
"successRate": 0.0391,
"total": 2020,
"unresolvedFailureCount": 1281
"total": 2023,
"unresolvedFailureCount": 1282
},
"warnings": [
"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。",
"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-x8 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-150 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 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 Ascend_910-b3 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 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 Biren_166m|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 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -10965,6 +11012,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2114,
"summarizedRecords": 2117,
"version": 1
}