state: generation 6485 (cycle)

This commit is contained in:
2026-09-13 02:57:24 +00:00
parent 8116e93661
commit 94db3da49e
9 changed files with 2243 additions and 2212 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T02:47:04.270444+00:00",
"lastSyncTime": "2026-09-13T02:47:03.906686+00:00",
"generatedAt": "2026-09-13T02:55:30.151645+00:00",
"lastSyncTime": "2026-09-13T02:55:29.910747+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -209,17 +209,19 @@
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T16:39:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T02:47:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T16:39:21+00:00",
"latestFailureAt": "2026-09-13T02:47:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B",
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4557197",
"4548919"
],
"targetGpu": "Ascend_910-b4",
@@ -1606,18 +1608,18 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 44,
"attributableFailureCount": 45,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 40,
"framework_architecture_unsupported": 41,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 79,
"failureCount": 80,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1627,7 +1629,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 79,
"total": 80,
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
@@ -2052,21 +2054,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 9,
"failureBreakdown": {
"参数/模板问题": 8,
"参数/模板问题": 9,
"验证失败": 48
},
"failureCount": 56,
"failureRate": 0.8615,
"failureCount": 57,
"failureRate": 0.8636,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.1385,
"successRate": 0.1364,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 65,
"unresolvedFailureCount": 56
"total": 66,
"unresolvedFailureCount": 57
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 53,
@@ -2193,21 +2195,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 1,
"参数/模板问题": 2,
"验证失败": 32
},
"failureCount": 33,
"failureRate": 0.9706,
"failureCount": 34,
"failureRate": 0.9714,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0294,
"successRate": 0.0286,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 33
"total": 35,
"unresolvedFailureCount": 34
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 44,
@@ -2471,28 +2473,28 @@
"model_load": 43,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1021,
"failureCount": 1023,
"failureRate": 0.9507,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 53,
"successRate": 0.0493,
"total": 1074,
"unresolvedFailureCount": 871
"total": 1076,
"unresolvedFailureCount": 873
},
"vllm": {
"attributableFailureCount": 290,
"attributableFailureCount": 291,
"decisionFailureRate": 0.9898,
"decisionSuccessRate": 0.0102,
"decisionTotal": 293,
"decisionTotal": 294,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 204,
"framework_architecture_unsupported": 205,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2501,14 +2503,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 516,
"failureCount": 517,
"failureRate": 0.9942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0058,
"total": 519,
"total": 520,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2613,7 +2615,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T02:47:04.265926+00:00",
"generatedAt": "2026-09-13T02:55:30.147369+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 30,
@@ -2639,13 +2641,13 @@
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
"attributableFailureCount": 45,
"decisionFailureRate": 0.9574,
"decisionSuccessRate": 0.0426,
"decisionTotal": 47,
"attributableFailureCount": 46,
"decisionFailureRate": 0.9583,
"decisionSuccessRate": 0.0417,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 40,
"framework_architecture_unsupported": 41,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -2653,14 +2655,14 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 268,
"failureCount": 269,
"failureRate": 0.9926,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0074,
"total": 270,
"total": 271,
"unresolvedFailureCount": 223
},
"Biren_166m": {
@@ -2833,18 +2835,18 @@
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 17,
"参数/模板问题": 18,
"验证失败": 48
},
"failureCount": 127,
"failureRate": 0.9137,
"failureCount": 128,
"failureRate": 0.9143,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0863,
"total": 139,
"unresolvedFailureCount": 74
"successRate": 0.0857,
"total": 140,
"unresolvedFailureCount": 75
},
"Mthreads_s4000": {
"attributableFailureCount": 36,
@@ -2883,18 +2885,18 @@
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 42,
"参数/模板问题": 9,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 93,
"failureRate": 0.9894,
"failureCount": 94,
"failureRate": 0.9895,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0106,
"total": 94,
"unresolvedFailureCount": 42
"successRate": 0.0105,
"total": 95,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
"attributableFailureCount": 50,
@@ -4485,21 +4487,21 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 7
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 8
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T23:26:15.638604+00:00",
"lastTerminalAt": "2026-09-13T02:55:29.910747+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4508,7 +4510,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 13
"unresolvedFailureCount": 12
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4746,6 +4748,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T02:55:29.910734+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
@@ -4833,21 +4860,23 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 0.5,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T17:24:58.529030+00:00",
"lastTerminalAt": "2026-09-13T02:55:29.910704+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"successRate": 0.5,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 14,
@@ -7362,41 +7391,40 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1753,
"totalRecords": 1840,
"terminalRecords": 1756,
"totalRecords": 1843,
"totals": {
"attributableFailureCount": 505,
"decisionFailureRate": 0.897,
"decisionSuccessRate": 0.103,
"decisionTotal": 563,
"attributableFailureCount": 506,
"decisionFailureRate": 0.8972,
"decisionSuccessRate": 0.1028,
"decisionTotal": 564,
"failureBreakdown": {
"ambiguous_runtime": 412,
"backend_operator": 42,
"framework_architecture_unsupported": 317,
"framework_architecture_unsupported": 318,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 48,
"参数/模板问题": 101,
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1695,
"failureRate": 0.9669,
"failureCount": 1698,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 58,
"successRate": 0.0331,
"total": 1753,
"unresolvedFailureCount": 1186
"successRate": 0.033,
"total": 1756,
"unresolvedFailureCount": 1188
},
"warnings": [
"GPU Ascend_910-b3 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 Sunrise_pt-200-x1 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 Cambricon_mlu-370-x4 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。",
@@ -7405,6 +7433,7 @@
"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-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。",
"组合 hygon_k100-ai|vllm-patch-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 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-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7427,6 +7456,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1840,
"summarizedRecords": 1843,
"version": 1
}