state: generation 20428 (cycle)
This commit is contained in:
@@ -3299,7 +3299,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-04T12:39:49.242111+00:00",
|
||||
"generatedAt": "2026-10-04T12:52:46.984506+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 166,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-04T12:51:32.966353+00:00",
|
||||
"generatedAt": "2026-10-04T12:54:43.351533+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-04T12:51:32.966353+00:00",
|
||||
"catalogUpdatedAt": "2026-10-04T12:54:43.351533+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-04T12:51:32.966353+00:00",
|
||||
"generatedAt": "2026-10-04T12:54:43.351533+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6557,6 +6557,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-04T12:51:32.966353+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-04T12:54:43.351533+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-04T11:49:17.442446+00:00",
|
||||
"lastSyncTime": "2026-10-04T11:49:17.148112+00:00",
|
||||
"generatedAt": "2026-10-04T12:52:46.902801+00:00",
|
||||
"lastSyncTime": "2026-10-04T12:52:46.641112+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2070,29 +2070,6 @@
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"iluvatar_bi-150|vllm|text-generation|model_type:mellum": {
|
||||
"architectureSignature": "model_type:mellum",
|
||||
"architectures": [],
|
||||
"evidenceCount": 3,
|
||||
"expiresAt": "2026-10-04T12:07:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-04T12:07:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "mellum",
|
||||
"sourceModelIds": [
|
||||
"JetBrains/Mellum2-12B-A2.5B-Thinking-SFT",
|
||||
"JetBrains/Mellum2-12B-A2.5B-Instruct",
|
||||
"JetBrains/Mellum2-12B-A2.5B-Thinking"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4152671",
|
||||
"4152323",
|
||||
"4152351"
|
||||
],
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"iluvatar_bi-150|vllm|text-generation|model_type:nemotron_h": {
|
||||
"architectureSignature": "model_type:nemotron_h",
|
||||
"architectures": [],
|
||||
@@ -3327,7 +3304,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 167,
|
||||
"activeBlockCount": 166,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 13,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 7,
|
||||
@@ -3340,7 +3317,7 @@
|
||||
"Cambricon_mlu-370-x8|vllm-customized": 6,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 5,
|
||||
"Iluvatar_bi-150|transformers": 5,
|
||||
"Iluvatar_bi-150|vllm": 7,
|
||||
"Iluvatar_bi-150|vllm": 6,
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
|
||||
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
|
||||
"Kunlunxin_p-800|vllm": 10,
|
||||
@@ -3450,25 +3427,25 @@
|
||||
"decisionSuccessRate": 0.0816,
|
||||
"decisionTotal": 49,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 89,
|
||||
"ambiguous_runtime": 90,
|
||||
"context_length": 9,
|
||||
"framework_architecture_unsupported": 35,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 143,
|
||||
"failureRate": 0.9728,
|
||||
"failureCount": 144,
|
||||
"failureRate": 0.973,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0272,
|
||||
"successRate": 0.027,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 147,
|
||||
"unresolvedFailureCount": 97
|
||||
"total": 148,
|
||||
"unresolvedFailureCount": 98
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 71,
|
||||
@@ -4915,27 +4892,27 @@
|
||||
"unresolvedFailureCount": 57
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 28,
|
||||
"decisionFailureRate": 0.6364,
|
||||
"decisionSuccessRate": 0.3636,
|
||||
"decisionTotal": 44,
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.6444,
|
||||
"decisionSuccessRate": 0.3556,
|
||||
"decisionTotal": 45,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"framework_architecture_unsupported": 25,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 40,
|
||||
"failureRate": 0.7143,
|
||||
"failureCount": 41,
|
||||
"failureRate": 0.7193,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 16,
|
||||
"successRate": 0.2857,
|
||||
"successRate": 0.2807,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 56,
|
||||
"total": 57,
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -6024,17 +6001,17 @@
|
||||
"unresolvedFailureCount": 6476
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3652,
|
||||
"attributableFailureCount": 3653,
|
||||
"decisionFailureRate": 0.9726,
|
||||
"decisionSuccessRate": 0.0274,
|
||||
"decisionTotal": 3755,
|
||||
"decisionTotal": 3756,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1597,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1378,
|
||||
"framework_architecture_unsupported": 1379,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 224,
|
||||
"platform_infrastructure": 876,
|
||||
@@ -6043,14 +6020,14 @@
|
||||
"tokenizer_compatibility": 420,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6175,
|
||||
"failureCount": 6176,
|
||||
"failureRate": 0.9836,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 876,
|
||||
"successCount": 103,
|
||||
"successRate": 0.0164,
|
||||
"total": 6278,
|
||||
"total": 6279,
|
||||
"unresolvedFailureCount": 1647
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -6178,7 +6155,7 @@
|
||||
"decisionSuccessRate": 0.0637,
|
||||
"decisionTotal": 157,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 203,
|
||||
"ambiguous_runtime": 204,
|
||||
"backend_operator": 15,
|
||||
"context_length": 9,
|
||||
"framework_architecture_unsupported": 90,
|
||||
@@ -6190,18 +6167,18 @@
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 29
|
||||
},
|
||||
"failureCount": 382,
|
||||
"failureRate": 0.9745,
|
||||
"failureCount": 383,
|
||||
"failureRate": 0.9746,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0255,
|
||||
"total": 392,
|
||||
"unresolvedFailureCount": 232
|
||||
"successRate": 0.0254,
|
||||
"total": 393,
|
||||
"unresolvedFailureCount": 233
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-04T11:49:17.393864+00:00",
|
||||
"generatedAt": "2026-10-04T12:52:46.890180+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 117,
|
||||
@@ -6209,7 +6186,7 @@
|
||||
"decisionSuccessRate": 0.1583,
|
||||
"decisionTotal": 139,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 158,
|
||||
"ambiguous_runtime": 159,
|
||||
"context_length": 9,
|
||||
"framework_architecture_unsupported": 102,
|
||||
"memory_capacity": 2,
|
||||
@@ -6220,15 +6197,15 @@
|
||||
"日志缺失": 3,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 346,
|
||||
"failureRate": 0.9402,
|
||||
"failureCount": 347,
|
||||
"failureRate": 0.9404,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.0598,
|
||||
"total": 368,
|
||||
"unresolvedFailureCount": 228
|
||||
"successRate": 0.0596,
|
||||
"total": 369,
|
||||
"unresolvedFailureCount": 229
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 329,
|
||||
@@ -6397,16 +6374,16 @@
|
||||
"unresolvedFailureCount": 1165
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 978,
|
||||
"decisionFailureRate": 0.8468,
|
||||
"decisionSuccessRate": 0.1532,
|
||||
"decisionTotal": 1155,
|
||||
"attributableFailureCount": 979,
|
||||
"decisionFailureRate": 0.8469,
|
||||
"decisionSuccessRate": 0.1531,
|
||||
"decisionTotal": 1156,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 352,
|
||||
"architecture_compatibility": 47,
|
||||
"backend_operator": 1,
|
||||
"context_length": 77,
|
||||
"framework_architecture_unsupported": 296,
|
||||
"framework_architecture_unsupported": 297,
|
||||
"memory_capacity": 219,
|
||||
"model_load": 87,
|
||||
"platform_infrastructure": 7,
|
||||
@@ -6417,14 +6394,14 @@
|
||||
"日志缺失": 6,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 1706,
|
||||
"failureRate": 0.906,
|
||||
"failureCount": 1707,
|
||||
"failureRate": 0.9061,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 7,
|
||||
"successCount": 177,
|
||||
"successRate": 0.094,
|
||||
"total": 1883,
|
||||
"successRate": 0.0939,
|
||||
"total": 1884,
|
||||
"unresolvedFailureCount": 721
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -6871,6 +6848,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "k2_horizon",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -17738,14 +17738,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 4
|
||||
"framework_architecture_unsupported": 5
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "qwen3_5_moe",
|
||||
@@ -17757,7 +17757,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none": {
|
||||
@@ -29191,6 +29191,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "k2_horizon",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -45698,14 +45722,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none|33": {
|
||||
"attributableFailureCount": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -45718,7 +45742,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none|34": {
|
||||
@@ -56549,20 +56573,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17287,
|
||||
"totalRecords": 17511,
|
||||
"terminalRecords": 17289,
|
||||
"totalRecords": 17513,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6204,
|
||||
"attributableFailureCount": 6205,
|
||||
"decisionFailureRate": 0.8641,
|
||||
"decisionSuccessRate": 0.1359,
|
||||
"decisionTotal": 7180,
|
||||
"decisionTotal": 7181,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4531,
|
||||
"ambiguous_runtime": 4532,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2236,
|
||||
"framework_architecture_unsupported": 2237,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 561,
|
||||
"platform_infrastructure": 948,
|
||||
@@ -56573,15 +56597,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16311,
|
||||
"failureCount": 16313,
|
||||
"failureRate": 0.9435,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 948,
|
||||
"successCount": 976,
|
||||
"successRate": 0.0565,
|
||||
"total": 17287,
|
||||
"unresolvedFailureCount": 9159
|
||||
"total": 17289,
|
||||
"unresolvedFailureCount": 9160
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -56641,6 +56665,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17511,
|
||||
"summarizedRecords": 17513,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user