state: generation 10972 (cycle)

This commit is contained in:
2026-09-20 23:05:16 +00:00
parent ffd7998d03
commit 605f0ae29f
9 changed files with 1806 additions and 1735 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T22:57:50.116179+00:00",
"lastSyncTime": "2026-09-20T22:57:49.771972+00:00",
"generatedAt": "2026-09-20T23:05:08.668302+00:00",
"lastSyncTime": "2026-09-20T23:05:08.270726+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3308,13 +3308,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 6,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 8
},
"failureCount": 29,
"failureCount": 30,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -3324,8 +3324,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 29,
"unresolvedFailureCount": 8
"total": 30,
"unresolvedFailureCount": 9
},
"Iluvatar_bi-150|unknown|asr": {
"attributableFailureCount": 0,
@@ -4890,21 +4890,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 43,
"ambiguous_runtime": 44,
"framework_architecture_unsupported": 7,
"memory_capacity": 5,
"model_load": 2,
"tokenizer_compatibility": 8
},
"failureCount": 65,
"failureCount": 66,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 65,
"unresolvedFailureCount": 43
"total": 66,
"unresolvedFailureCount": 44
},
"unknown": {
"attributableFailureCount": 1857,
@@ -5102,7 +5102,7 @@
"unresolvedFailureCount": 38
}
},
"generatedAt": "2026-09-20T22:57:50.106858+00:00",
"generatedAt": "2026-09-20T23:05:08.659060+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 87,
@@ -5269,7 +5269,7 @@
"decisionSuccessRate": 0.168,
"decisionTotal": 887,
"failureBreakdown": {
"ambiguous_runtime": 615,
"ambiguous_runtime": 616,
"architecture_compatibility": 15,
"backend_operator": 11,
"context_length": 29,
@@ -5284,15 +5284,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1879,
"failureRate": 0.9265,
"failureCount": 1880,
"failureRate": 0.9266,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0735,
"total": 2028,
"unresolvedFailureCount": 1120
"successRate": 0.0734,
"total": 2029,
"unresolvedFailureCount": 1121
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 964,
@@ -8590,6 +8590,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|plamo3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"modelType": "plamo3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -13266,18 +13289,18 @@
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 10,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 9,
"framework_architecture_unsupported": 8,
"tokenizer_compatibility": 1
},
"failureCount": 15,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -13289,7 +13312,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 15,
"total": 14,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|unknown|text-generation": {
@@ -13528,23 +13551,23 @@
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 15,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 5,
"memory_capacity": 3,
"tokenizer_compatibility": 7
"tokenizer_compatibility": 6
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T21:06:45.850266+00:00",
"lastTerminalAt": "2026-09-20T23:05:08.270726+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -13553,7 +13576,7 @@
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 5
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 9,
@@ -15633,6 +15656,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|plamo3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-20T23:05:08.270726+00:00",
"modelType": "plamo3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|modelopt": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -21586,6 +21634,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|plamo3|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"loadSizeLog2Bucket": 33,
"modelType": "plamo3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -28483,15 +28555,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 15994,
"totalRecords": 16158,
"terminalRecords": 15995,
"totalRecords": 16159,
"totals": {
"attributableFailureCount": 5817,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6749,
"failureBreakdown": {
"ambiguous_runtime": 3819,
"ambiguous_runtime": 3820,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -28507,15 +28579,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15062,
"failureCount": 15063,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 932,
"successRate": 0.0583,
"total": 15994,
"unresolvedFailureCount": 8323
"total": 15995,
"unresolvedFailureCount": 8324
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -28562,12 +28634,12 @@
"组合 Cambricon_mlu-370-x4|unknown|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 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。",
"组合 Iluvatar_bi-150|transformers|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 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 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 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 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": 16158,
"summarizedRecords": 16159,
"version": 1
}