state: generation 6232 (cycle)

This commit is contained in:
2026-09-12 14:14:50 +00:00
parent d9f3e26435
commit 2cdc5b0af0
9 changed files with 2045 additions and 2045 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T13:37:49.813166+00:00",
"lastSyncTime": "2026-09-12T13:37:49.606306+00:00",
"generatedAt": "2026-09-12T14:12:46.471291+00:00",
"lastSyncTime": "2026-09-12T14:12:46.256625+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -208,17 +208,17 @@
"architectureSignature": "model_type:nemotron_h",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-05T01:01:21+00:00",
"expiresAt": "2026-10-12T14:11:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-05T01:01:21+00:00",
"latestFailureAt": "2026-09-12T14:11:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "nemotron_h",
"sourceModelIds": [
"nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15"
"primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8"
],
"sourceTaskIds": [
"4257506"
"4543480"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
@@ -1539,18 +1539,18 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 39,
"attributableFailureCount": 40,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 39,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 35,
"framework_architecture_unsupported": 36,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 74,
"failureCount": 75,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1560,7 +1560,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 74,
"total": 75,
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
@@ -2417,14 +2417,14 @@
"unresolvedFailureCount": 866
},
"vllm": {
"attributableFailureCount": 272,
"attributableFailureCount": 273,
"decisionFailureRate": 0.9891,
"decisionSuccessRate": 0.0109,
"decisionTotal": 275,
"decisionTotal": 276,
"failureBreakdown": {
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 186,
"framework_architecture_unsupported": 187,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2433,14 +2433,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 497,
"failureCount": 498,
"failureRate": 0.994,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.006,
"total": 500,
"total": 501,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
@@ -2545,7 +2545,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T13:37:49.808132+00:00",
"generatedAt": "2026-09-12T14:12:46.465723+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 27,
@@ -2571,13 +2571,13 @@
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
"attributableFailureCount": 40,
"decisionFailureRate": 0.9524,
"decisionSuccessRate": 0.0476,
"decisionTotal": 42,
"attributableFailureCount": 41,
"decisionFailureRate": 0.9535,
"decisionSuccessRate": 0.0465,
"decisionTotal": 43,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 35,
"framework_architecture_unsupported": 36,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -2585,14 +2585,14 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 263,
"failureCount": 264,
"failureRate": 0.9925,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0075,
"total": 265,
"total": 266,
"unresolvedFailureCount": 223
},
"Biren_166m": {
@@ -4339,7 +4339,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T09:44:49.014179+00:00",
"lastTerminalAt": "2026-09-12T14:12:46.256625+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4436,9 +4436,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
@@ -4450,8 +4450,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -7256,17 +7256,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1721,
"totalRecords": 1808,
"terminalRecords": 1722,
"totalRecords": 1809,
"totals": {
"attributableFailureCount": 482,
"decisionFailureRate": 0.8942,
"decisionSuccessRate": 0.1058,
"decisionTotal": 539,
"attributableFailureCount": 483,
"decisionFailureRate": 0.8944,
"decisionSuccessRate": 0.1056,
"decisionTotal": 540,
"failureBreakdown": {
"ambiguous_runtime": 404,
"backend_operator": 42,
"framework_architecture_unsupported": 295,
"framework_architecture_unsupported": 296,
"memory_capacity": 11,
"model_load": 72,
"platform_infrastructure": 4,
@@ -7276,20 +7276,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1664,
"failureCount": 1665,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0331,
"total": 1721,
"total": 1722,
"unresolvedFailureCount": 1178
},
"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。",
@@ -7298,7 +7299,6 @@
"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。",
@@ -7320,6 +7320,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1808,
"summarizedRecords": 1809,
"version": 1
}