state: generation 13283 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-23T02:06:47.498515+00:00",
|
||||
"lastSyncTime": "2026-09-23T02:06:44.350388+00:00",
|
||||
"generatedAt": "2026-09-23T02:15:14.481703+00:00",
|
||||
"lastSyncTime": "2026-09-23T02:15:13.670755+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -5158,28 +5158,28 @@
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 102,
|
||||
"attributableFailureCount": 103,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 102,
|
||||
"decisionTotal": 103,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 8,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 12,
|
||||
"platform_infrastructure": 18,
|
||||
"platform_infrastructure": 19,
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 126,
|
||||
"failureCount": 128,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 18,
|
||||
"platformFailureCount": 19,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 126,
|
||||
"total": 128,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -5835,28 +5835,28 @@
|
||||
"unresolvedFailureCount": 25
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 134,
|
||||
"decisionFailureRate": 0.964,
|
||||
"decisionSuccessRate": 0.036,
|
||||
"decisionTotal": 139,
|
||||
"attributableFailureCount": 135,
|
||||
"decisionFailureRate": 0.9643,
|
||||
"decisionSuccessRate": 0.0357,
|
||||
"decisionTotal": 140,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 298,
|
||||
"backend_operator": 8,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 29,
|
||||
"memory_capacity": 10,
|
||||
"model_load": 5,
|
||||
"platform_infrastructure": 18,
|
||||
"platform_infrastructure": 19,
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 463,
|
||||
"failureRate": 0.9893,
|
||||
"failureCount": 465,
|
||||
"failureRate": 0.9894,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 18,
|
||||
"platformFailureCount": 19,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0107,
|
||||
"total": 468,
|
||||
"successRate": 0.0106,
|
||||
"total": 470,
|
||||
"unresolvedFailureCount": 311
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -5888,7 +5888,7 @@
|
||||
"unresolvedFailureCount": 175
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-23T02:06:47.486688+00:00",
|
||||
"generatedAt": "2026-09-23T02:15:14.468487+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6222,32 +6222,32 @@
|
||||
"unresolvedFailureCount": 297
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 732,
|
||||
"decisionFailureRate": 0.8894,
|
||||
"decisionSuccessRate": 0.1106,
|
||||
"decisionTotal": 823,
|
||||
"attributableFailureCount": 733,
|
||||
"decisionFailureRate": 0.8896,
|
||||
"decisionSuccessRate": 0.1104,
|
||||
"decisionTotal": 824,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
"backend_operator": 35,
|
||||
"backend_operator": 36,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 154,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 221,
|
||||
"platform_infrastructure": 222,
|
||||
"repository_structure": 83,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 263,
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1375,
|
||||
"failureRate": 0.9379,
|
||||
"failureCount": 1377,
|
||||
"failureRate": 0.938,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 221,
|
||||
"platformFailureCount": 222,
|
||||
"successCount": 91,
|
||||
"successRate": 0.0621,
|
||||
"total": 1466,
|
||||
"successRate": 0.062,
|
||||
"total": 1468,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -18908,14 +18908,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 5,
|
||||
"attributableFailureCount": 6,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 5,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 5
|
||||
"backend_operator": 6
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "llama",
|
||||
@@ -18927,7 +18927,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
|
||||
@@ -21223,26 +21223,26 @@
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 1,
|
||||
"consecutivePlatformFailures": 2,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"platform_infrastructure": 1
|
||||
"platform_infrastructure": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-23T01:50:08+00:00",
|
||||
"lastTerminalAt": "2026-09-23T01:50:30.356465+00:00",
|
||||
"lastPlatformFailureAt": "2026-09-23T02:14:08+00:00",
|
||||
"lastTerminalAt": "2026-09-23T02:15:13.670721+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|unknown|text-generation": {
|
||||
@@ -21625,31 +21625,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-21T12:58:50.741501+00:00",
|
||||
"modelType": "gemma4",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|hrm_text|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -43262,14 +43237,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq|32": {
|
||||
"attributableFailureCount": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 4
|
||||
"backend_operator": 5
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -43282,7 +43257,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq|33": {
|
||||
@@ -45755,23 +45730,23 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16792,
|
||||
"totalRecords": 17010,
|
||||
"terminalRecords": 16794,
|
||||
"totalRecords": 17012,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6011,
|
||||
"attributableFailureCount": 6012,
|
||||
"decisionFailureRate": 0.8622,
|
||||
"decisionSuccessRate": 0.1378,
|
||||
"decisionTotal": 6972,
|
||||
"decisionTotal": 6973,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4282,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 113,
|
||||
"backend_operator": 114,
|
||||
"context_length": 322,
|
||||
"framework_architecture_unsupported": 2132,
|
||||
"memory_capacity": 1203,
|
||||
"model_load": 526,
|
||||
"platform_infrastructure": 930,
|
||||
"platform_infrastructure": 931,
|
||||
"repository_structure": 740,
|
||||
"runtime_memory": 91,
|
||||
"tokenizer_compatibility": 669,
|
||||
@@ -45779,20 +45754,19 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 15831,
|
||||
"failureCount": 15833,
|
||||
"failureRate": 0.9428,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 930,
|
||||
"platformFailureCount": 931,
|
||||
"successCount": 961,
|
||||
"successRate": 0.0572,
|
||||
"total": 16792,
|
||||
"total": 16794,
|
||||
"unresolvedFailureCount": 8890
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 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-x8 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。",
|
||||
@@ -45801,8 +45775,9 @@
|
||||
"GPU hygon_k100-ai 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 Vastai_va16 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 Mthreads_s4000 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 Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|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。",
|
||||
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -45826,7 +45801,6 @@
|
||||
"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 MetaX_c-500|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_bi-150|vllm_0_17_0_corex_4_4_0|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 Ascend_910-b4|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。",
|
||||
"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 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -45840,10 +45814,11 @@
|
||||
"组合 Mthreads_s4000|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 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。",
|
||||
"组合 MetaX_c-500|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 hygon_k100-ai|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 hygon_k100-ai|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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17010,
|
||||
"summarizedRecords": 17012,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user