state: generation 5102 (cycle)

This commit is contained in:
2026-09-10 09:49:20 +00:00
parent d5ad209faa
commit 184766a83e
9 changed files with 2219 additions and 2221 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T09:38:19.296061+00:00",
"lastSyncTime": "2026-09-10T09:38:19.106782+00:00",
"generatedAt": "2026-09-10T09:47:33.599443+00:00",
"lastSyncTime": "2026-09-10T09:47:33.262404+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2147,12 +2147,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 94,
"failureCount": 95,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2162,8 +2162,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 94,
"unresolvedFailureCount": 50
"total": 95,
"unresolvedFailureCount": 51
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2235,14 +2235,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 48,
"failureCount": 49,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2252,8 +2252,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 48,
"unresolvedFailureCount": 13
"total": 49,
"unresolvedFailureCount": 14
}
},
"frameworkSummaries": {
@@ -2325,7 +2325,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 155,
"ambiguous_runtime": 157,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2336,15 +2336,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 412,
"failureCount": 414,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 413,
"unresolvedFailureCount": 176
"total": 415,
"unresolvedFailureCount": 178
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2447,7 +2447,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T09:38:19.291073+00:00",
"generatedAt": "2026-09-10T09:47:33.595423+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2731,22 +2731,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 51,
"ambiguous_runtime": 52,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 241,
"failureRate": 0.9488,
"failureCount": 242,
"failureRate": 0.949,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0512,
"total": 254,
"unresolvedFailureCount": 194
"successRate": 0.051,
"total": 255,
"unresolvedFailureCount": 195
},
"hygon_k100-ai": {
"attributableFailureCount": 38,
@@ -2754,7 +2754,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2763,15 +2763,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 88,
"failureCount": 89,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 88,
"unresolvedFailureCount": 50
"total": 89,
"unresolvedFailureCount": 51
}
},
"observedGpuMemoryGiB": {
@@ -4334,9 +4334,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 6
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4348,8 +4348,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 6,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -4563,11 +4563,9 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 0.5,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:32:11.428244+00:00",
@@ -4575,11 +4573,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.5,
"successRate": 1.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 1,
@@ -4607,21 +4605,21 @@
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T06:56:22.046035+00:00",
"lastTerminalAt": "2026-09-10T09:47:33.262382+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4630,7 +4628,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 18
"unresolvedFailureCount": 19
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -4690,16 +4688,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T07:04:57.311815+00:00",
"lastTerminalAt": "2026-09-10T09:47:33.262404+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4707,8 +4705,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 10
"total": 19,
"unresolvedFailureCount": 11
}
},
"recentProfileCombinationStats": {
@@ -7058,15 +7056,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1551,
"totalRecords": 1638,
"terminalRecords": 1553,
"totalRecords": 1640,
"totals": {
"attributableFailureCount": 405,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 456,
"failureBreakdown": {
"ambiguous_runtime": 325,
"ambiguous_runtime": 327,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7078,21 +7076,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1500,
"failureRate": 0.9671,
"failureCount": 1502,
"failureRate": 0.9672,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 51,
"successRate": 0.0329,
"total": 1551,
"unresolvedFailureCount": 1093
"successRate": 0.0328,
"total": 1553,
"unresolvedFailureCount": 1095
},
"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。",
@@ -7100,7 +7098,7 @@
"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。",
@@ -7121,6 +7119,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1638,
"summarizedRecords": 1640,
"version": 1
}