state: generation 4870 (cycle)

This commit is contained in:
2026-09-10 00:53:16 +00:00
parent 5525f4a41b
commit 2284993996
10 changed files with 2277 additions and 2255 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T00:20:21.698699+00:00",
"lastSyncTime": "2026-09-10T00:20:21.332944+00:00",
"generatedAt": "2026-09-10T00:51:37.700651+00:00",
"lastSyncTime": "2026-09-10T00:51:37.399593+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1904,19 +1904,19 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 37,
"attributableFailureCount": 38,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 18,
"backend_operator": 19,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 9
},
"failureCount": 53,
"failureCount": 54,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1926,7 +1926,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 53,
"total": 54,
"unresolvedFailureCount": 16
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2140,12 +2140,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 46,
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 90,
"failureCount": 91,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2155,8 +2155,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 90,
"unresolvedFailureCount": 46
"total": 91,
"unresolvedFailureCount": 47
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2313,13 +2313,13 @@
"unresolvedFailureCount": 822
},
"vllm": {
"attributableFailureCount": 226,
"attributableFailureCount": 227,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 226,
"decisionTotal": 227,
"failureBreakdown": {
"ambiguous_runtime": 124,
"backend_operator": 21,
"ambiguous_runtime": 125,
"backend_operator": 22,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
"model_load": 18,
@@ -2329,15 +2329,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 372,
"failureCount": 374,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 372,
"unresolvedFailureCount": 145
"total": 374,
"unresolvedFailureCount": 146
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2440,7 +2440,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T00:20:21.694540+00:00",
"generatedAt": "2026-09-10T00:51:37.696533+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2647,27 +2647,27 @@
"unresolvedFailureCount": 75
},
"MetaX_c-500": {
"attributableFailureCount": 37,
"decisionFailureRate": 0.8043,
"decisionSuccessRate": 0.1957,
"decisionTotal": 46,
"attributableFailureCount": 38,
"decisionFailureRate": 0.8085,
"decisionSuccessRate": 0.1915,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 18,
"backend_operator": 19,
"framework_architecture_unsupported": 14,
"memory_capacity": 1,
"model_load": 4,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 109,
"failureRate": 0.9237,
"failureCount": 110,
"failureRate": 0.9244,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0763,
"total": 118,
"successRate": 0.0756,
"total": 119,
"unresolvedFailureCount": 72
},
"Mthreads_s4000": {
@@ -2724,22 +2724,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 47,
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 237,
"failureRate": 0.948,
"failureCount": 238,
"failureRate": 0.9482,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.052,
"total": 250,
"unresolvedFailureCount": 190
"successRate": 0.0518,
"total": 251,
"unresolvedFailureCount": 191
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
@@ -3474,14 +3474,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 8,
"attributableFailureCount": 9,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"backend_operator": 8
"backend_operator": 9
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -3493,7 +3493,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -4555,21 +4555,21 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|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": 14,
"framework_architecture_unsupported": 6
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 5
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T00:20:21.332898+00:00",
"lastTerminalAt": "2026-09-10T00:51:37.399566+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4578,7 +4578,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 14
"unresolvedFailureCount": 15
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -6144,6 +6144,30 @@
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
@@ -6721,16 +6745,16 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1468,
"totalRecords": 1552,
"terminalRecords": 1470,
"totalRecords": 1554,
"totals": {
"attributableFailureCount": 389,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 437,
"attributableFailureCount": 390,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 438,
"failureBreakdown": {
"ambiguous_runtime": 262,
"backend_operator": 24,
"ambiguous_runtime": 263,
"backend_operator": 25,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
"model_load": 45,
@@ -6741,21 +6765,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1420,
"failureCount": 1422,
"failureRate": 0.9673,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0327,
"total": 1468,
"unresolvedFailureCount": 1029
"total": 1470,
"unresolvedFailureCount": 1030
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 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。",
@@ -6763,7 +6787,7 @@
"GPU hygon_k100-ai 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 Mthreads_s4000 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。",
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x8|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 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。",
@@ -6784,6 +6808,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1552,
"summarizedRecords": 1554,
"version": 1
}