state: generation 37800 (intent)
This commit is contained in:
@@ -567,7 +567,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-26T04:00:15.437512+00:00",
|
||||
"generatedAt": "2026-10-26T04:01:53.490828+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 28,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -452,7 +452,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-26T04:00:15.560082+00:00",
|
||||
"generatedAt": "2026-10-26T04:01:53.564829+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-26T04:00:15.560082+00:00",
|
||||
"catalogUpdatedAt": "2026-10-26T04:01:53.564829+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-26T04:00:15.560082+00:00",
|
||||
"generatedAt": "2026-10-26T04:01:53.564829+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6493,6 +6493,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-26T04:00:15.560082+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-26T04:01:53.564829+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-26T03:48:39.958383+00:00",
|
||||
"lastSyncTime": "2026-10-26T03:48:39.664901+00:00",
|
||||
"generatedAt": "2026-10-26T04:01:53.384873+00:00",
|
||||
"lastSyncTime": "2026-10-26T04:01:53.066171+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1147,25 +1147,25 @@
|
||||
"decisionSuccessRate": 0.1957,
|
||||
"decisionTotal": 46,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 58,
|
||||
"ambiguous_runtime": 60,
|
||||
"framework_architecture_unsupported": 33,
|
||||
"model_load": 4,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 10,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 109,
|
||||
"failureRate": 0.9237,
|
||||
"failureCount": 111,
|
||||
"failureRate": 0.925,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 9,
|
||||
"successRate": 0.0763,
|
||||
"successRate": 0.075,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 118,
|
||||
"unresolvedFailureCount": 71
|
||||
"total": 120,
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -2931,23 +2931,23 @@
|
||||
"decisionSuccessRate": 0.1136,
|
||||
"decisionTotal": 44,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"ambiguous_runtime": 29,
|
||||
"framework_architecture_unsupported": 26,
|
||||
"model_load": 13,
|
||||
"参数/模板问题": 5
|
||||
},
|
||||
"failureCount": 72,
|
||||
"failureRate": 0.9351,
|
||||
"failureCount": 73,
|
||||
"failureRate": 0.9359,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0649,
|
||||
"successRate": 0.0641,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 33
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 34
|
||||
},
|
||||
"Vastai_va16|vllm|text-generation": {
|
||||
"attributableFailureCount": 430,
|
||||
@@ -3350,7 +3350,7 @@
|
||||
"decisionSuccessRate": 0.2588,
|
||||
"decisionTotal": 85,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 122,
|
||||
"ambiguous_runtime": 124,
|
||||
"framework_architecture_unsupported": 55,
|
||||
"model_load": 7,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -3358,15 +3358,15 @@
|
||||
"参数/模板问题": 57,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 246,
|
||||
"failureRate": 0.9179,
|
||||
"failureCount": 248,
|
||||
"failureRate": 0.9185,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.0821,
|
||||
"total": 268,
|
||||
"unresolvedFailureCount": 182
|
||||
"successRate": 0.0815,
|
||||
"total": 270,
|
||||
"unresolvedFailureCount": 184
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 71,
|
||||
@@ -3421,7 +3421,7 @@
|
||||
"decisionSuccessRate": 0.0347,
|
||||
"decisionTotal": 202,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 453,
|
||||
"ambiguous_runtime": 454,
|
||||
"backend_operator": 11,
|
||||
"framework_architecture_unsupported": 59,
|
||||
"memory_capacity": 11,
|
||||
@@ -3430,15 +3430,15 @@
|
||||
"tokenizer_compatibility": 101,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 734,
|
||||
"failureCount": 735,
|
||||
"failureRate": 0.9906,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 36,
|
||||
"successCount": 7,
|
||||
"successRate": 0.0094,
|
||||
"total": 741,
|
||||
"unresolvedFailureCount": 503
|
||||
"total": 742,
|
||||
"unresolvedFailureCount": 504
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 182,
|
||||
@@ -3469,7 +3469,7 @@
|
||||
"unresolvedFailureCount": 366
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-26T03:48:39.943406+00:00",
|
||||
"generatedAt": "2026-10-26T04:01:53.368228+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 134,
|
||||
@@ -3563,7 +3563,7 @@
|
||||
"decisionSuccessRate": 0.0876,
|
||||
"decisionTotal": 845,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 523,
|
||||
"ambiguous_runtime": 525,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 323,
|
||||
@@ -3576,15 +3576,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1685,
|
||||
"failureRate": 0.9579,
|
||||
"failureCount": 1687,
|
||||
"failureRate": 0.958,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 74,
|
||||
"successRate": 0.0421,
|
||||
"total": 1759,
|
||||
"unresolvedFailureCount": 898
|
||||
"successRate": 0.042,
|
||||
"total": 1761,
|
||||
"unresolvedFailureCount": 900
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 72,
|
||||
@@ -3840,7 +3840,7 @@
|
||||
"decisionSuccessRate": 0.108,
|
||||
"decisionTotal": 528,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 828,
|
||||
"ambiguous_runtime": 829,
|
||||
"context_length": 9,
|
||||
"framework_architecture_unsupported": 205,
|
||||
"memory_capacity": 133,
|
||||
@@ -3852,15 +3852,15 @@
|
||||
"日志缺失": 124,
|
||||
"验证失败": 130
|
||||
},
|
||||
"failureCount": 1826,
|
||||
"failureCount": 1827,
|
||||
"failureRate": 0.9697,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 14,
|
||||
"successCount": 57,
|
||||
"successRate": 0.0303,
|
||||
"total": 1883,
|
||||
"unresolvedFailureCount": 1341
|
||||
"total": 1884,
|
||||
"unresolvedFailureCount": 1342
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 752,
|
||||
@@ -9770,10 +9770,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"ambiguous_runtime": 3,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "k2_horizon",
|
||||
@@ -9785,8 +9785,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -10371,9 +10371,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "qwen3",
|
||||
@@ -10385,8 +10385,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -24392,6 +24392,29 @@
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|granite|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "granite",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|hrm_text|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -26921,13 +26944,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-10-10T13:57:15.079577+00:00",
|
||||
"lastTerminalAt": "2026-10-26T04:01:53.066133+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -26935,8 +26958,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -27387,9 +27410,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 5
|
||||
"参数/模板问题": 4
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -27401,8 +27424,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -27607,6 +27630,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastTerminalAt": "2026-10-26T04:01:53.066133+00:00",
|
||||
"modelType": "qwen3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -38902,10 +38950,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"ambiguous_runtime": 2,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -38918,8 +38966,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -39933,6 +39981,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
"modelType": "qwen3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -60853,6 +60925,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|granite|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "granite",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm_fix_tokenizer|text-generation|hrm_text|none|31": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -64366,15 +64462,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 18120,
|
||||
"totalRecords": 18664,
|
||||
"terminalRecords": 18123,
|
||||
"totalRecords": 18667,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6392,
|
||||
"decisionFailureRate": 0.8664,
|
||||
"decisionSuccessRate": 0.1336,
|
||||
"decisionTotal": 7378,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4709,
|
||||
"ambiguous_runtime": 4712,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 137,
|
||||
@@ -64390,15 +64486,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 17134,
|
||||
"failureCount": 17137,
|
||||
"failureRate": 0.9456,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 972,
|
||||
"successCount": 986,
|
||||
"successRate": 0.0544,
|
||||
"total": 18120,
|
||||
"unresolvedFailureCount": 9770
|
||||
"total": 18123,
|
||||
"unresolvedFailureCount": 9773
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -64450,17 +64546,17 @@
|
||||
"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。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm-customized|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_mrv-100|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 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|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 MetaX_c-500|vllm|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 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 Vastai_va16|vllm_fix_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 Sunrise_pt-200-x1|vllm_fix_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 Mthreads_s4000|llamacpp|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-x4|vllm-mlu|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-mlu|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": 18664,
|
||||
"summarizedRecords": 18667,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-25T07:12:33.440912+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-25T07:11:36+00:00", "targetGpu": "MetaX_c-500", "taskId": "5669006", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-10-26T04:01:53.066133+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "failed", "status": "success", "submitTime": "2026-10-24T20:16:08.741643+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766395", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T04:12:56.440372+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "failed", "status": "success", "submitTime": "2026-10-24T10:37:32.836646+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5758987", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T07:12:33.440966+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859917848, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859917848}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-24T04:23:11.562135+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5753394", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-23T14:45:02.363525+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-23T14:44:16+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5373903", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-10-26T03:39:43.273211+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "1808282a6a7e87463f4fe68a059e74642ad7fba49ec04a246f0c3ea29ccfa12b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:35:46.372146+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320887", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-26T00:00:53.366321+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.366014+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320893", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164561+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164611+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
@@ -3898,6 +3898,18 @@
|
||||
{"batchId": "317f88a7469149eba26eeb0dbe5381f5", "completedAt": "2026-10-26T03:22:16.682367+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:22:14.660052+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f39ccaa503784d0a868963bed76891ad", "lastModified": "2026-10-21T17:04:48+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T04:00:21.526916+00:00", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795258", "taskType": "text-generation"}
|
||||
{"batchId": "5da74afbb0ac4f318ee9d2f649e4d5f9", "completedAt": "2026-10-26T03:23:08.952583+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:23:06.723325+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f1bde58b6eca41469d50b4bd47d412c7", "lastModified": "2026-10-21T17:19:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T04:00:21.528666+00:00", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795272", "taskType": "text-generation"}
|
||||
{"batchId": "5da74afbb0ac4f318ee9d2f649e4d5f9", "completedAt": "2026-10-26T03:23:08.952600+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:23:06.723545+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0bdb791fc27f48b991932ee1f5eeecae", "lastModified": "2026-10-21T18:39:01+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "reason": null, "reconciledAt": "2026-10-26T04:00:21.528930+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795271", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009408+00:00", "framework": "vllm_tokenizer_patch", "intentId": "eb792de176cc40dea1b74bdecc89b582", "lastModified": "2026-10-25T18:35:45+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nanbeige4.3-33B-FP8", "repoId": "primitive-ai/Nanbeige4.3-33B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009500+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e6013ffa5b24ad896703b3990ca8c31", "lastModified": "2026-10-21T16:25:01+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009550+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5c92616a4404b6697d70cedfc173823", "lastModified": "2026-10-25T15:10:11+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-MoVA-36B-A4B-FP8", "repoId": "IFM/Jais-3-MoVA-36B-A4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009593+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a0051e701f894257b6db258783f9eae2", "lastModified": "2026-10-21T16:14:40+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009636+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6082fd591ef34501b99fe1954dfc00b9", "lastModified": "2026-10-21T16:52:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-70B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-70B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009679+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7789e4c1638246a7b45a81c2084112f2", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009721+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3f438be550d34dec88aff5bfd15057ed", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce7d1b380fd1441da4372e6459a6ed10", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009806+00:00", "framework": "vllm_fix_tokenizer", "intentId": "657f675776ba46a6b854b872f0712e39", "lastModified": "2026-10-21T17:19:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-8bit", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009847+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8bf3da0a9a724cd382d7f6c920b447cc", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009890+00:00", "framework": "vllm_fix_tokenizer", "intentId": "80ed6c6bc66b46718752315a65348fba", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "ca286dd687f748e4bfef9e3058eabff8", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:01:56.009932+00:00", "framework": "vllm_fix_tokenizer", "intentId": "29b9de645cf9463b9fa6a9fa685bc571", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "bdb6658acaea404d95c43cc8f2aed6e7", "completedAt": "2026-10-26T04:00:19.748363+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:00:17.276369+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e3993c2095d54575b7d0395fcee2b2ae", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "bdb6658acaea404d95c43cc8f2aed6e7", "completedAt": "2026-10-26T04:00:19.748361+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:00:17.276326+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10fae5d8f4b44cc3a31602fe2e0f226e", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "bdb6658acaea404d95c43cc8f2aed6e7", "completedAt": "2026-10-26T04:00:19.748358+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:00:17.276284+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0a7ca30df298459a9a7398037686a1cc", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "ff12f11e75f3a4dfce6f685dd05ac4afd8fda0da578c739d678843c0f332070b",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "64b59ff539dbfe9e47379c8f4ad69e9470df70e9ce2dbc63c1ebfbdc986e46d8",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "93ac6dd95c4dfc761dada5a32981583aa36ed6fcbed4b2d142cebb318070d598",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "621e82ae0ab53e2789ec8dcd6bd9d4da87d0cfd737ba500fd206575da5280f9f",
|
||||
".modelhub_state/official_capabilities.json": "bcbf87086c23df235e255bd4725ba31fd8ec7f48d2f32d0da158edb88e083d24",
|
||||
".modelhub_state/outcome_checkpoint.json": "347a0334548a76cdb44cecf7dd6b8ac90b4bc0ac0e90b8027f8de428a52d27fd",
|
||||
".modelhub_state/market_intelligence.json": "49baf1faee02afb42efed7fd0aa8dfe6be75d059b65fc402ac8e704572ecace8",
|
||||
".modelhub_state/official_capabilities.json": "2e583d297a9223880c24384f9345fb4adb34506d415513e2b2e8f2656ddebe13",
|
||||
".modelhub_state/outcome_checkpoint.json": "dd7fa06f25d346859b4a5c82cc551e3b49ebf64a3eacdcf4c4ebebec073d7097",
|
||||
".modelhub_state/queue_cleanup_latest.json": "ead7cb09cb02a3371450ddc7323bbaa0ac96be41a6d2e540a2d9e78a72aed091",
|
||||
".modelhub_state/recent_outcomes.jsonl": "4f41069928e19caf172ad75afe3b24c9de4c1a48122c7348f8438e46a9aedb7f",
|
||||
".modelhub_state/recent_outcomes.jsonl": "28643eac175d15dea638020588f9d1491b83dfe0146ecc6b92a56413a2988564",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "2b373a8701156bb1502d5f0cadf1512816e62d39de1fecaa065884e90c9c62b1",
|
||||
".modelhub_state/recovery_intents.jsonl": "ff2521a48cdd549d03adb9634e565aac31ed460d8893c25dbc4ad160d8d52157",
|
||||
".modelhub_state/recovery_intents.jsonl": "08555e303baf2775a2982eee6947dc1c0235e09c3a99e2302dfb12240f904b2b",
|
||||
".modelhub_state/routing_intelligence.json": "100f674550d4848b25fc3060511fee441fe7c3aa80861a938e5b4d914789efbf",
|
||||
".modelhub_state/submission_exclusions.jsonl": "3db506f4d37bc78a9069d6022969e3718fa3eb1dad129907c99f63d5a7300ba1",
|
||||
".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9",
|
||||
"ledger/submissions.jsonl": "467f576bc5742163724d86e4e9d2f7228e05bd008beb603032107d47c8a76f47",
|
||||
"outcomes/submissions.jsonl": "46014214673252fe0aad8262dfe3dcf7b55f2683d37ea5ceca3328b1ac323cd1"
|
||||
"outcomes/submissions.jsonl": "8cc5ad9a3345f780b4fa4eda6a6fd4a7abe836091af8bd22b672b7468966a6dd"
|
||||
},
|
||||
"generation": 37799,
|
||||
"phase": "cycle",
|
||||
"generation": 37800,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-26T04:00:21.743345+00:00",
|
||||
"updatedAt": "2026-10-26T04:01:56.178364+00:00",
|
||||
"writerId": "dffce16061d848e398e5b5b22f649ccc"
|
||||
}
|
||||
|
||||
@@ -167,7 +167,6 @@
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:24:00.455827+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:21:33.668586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054819", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-25T03:12:25.055935+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T19:09:46.549452+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5067112", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-25T04:01:29.477054+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 7.111, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": null, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 550792704, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6362590564}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T19:58:03.287508+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5067706", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-25T04:32:54.853030+00:00", "modelId": "bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "6070792dbccc0c99f5d8084cd735fc62b3a83b09a4192b662e3ec76ed05d0097", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1077324288, "estimatedRequiredGiB": 30.563, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:reasoning", "custom_tag:mathematical", "custom_tag:hybrid-reasoning", "custom_tag:adaptive-reasoning", "custom_tag:efficient-reasoning", "custom_tag:reinforcement-learning", "custom_tag:rlvr", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27347406407}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T20:29:28.351567+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5068184", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-25T04:49:22.358498+00:00", "modelId": "bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b14915854fdddc06b6a8c39ae8b301bc36a6f8013c018c670701ab21e4acf1d5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1077324288, "estimatedRequiredGiB": 30.563, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:reasoning", "custom_tag:mathematical", "custom_tag:hybrid-reasoning", "custom_tag:adaptive-reasoning", "custom_tag:efficient-reasoning", "custom_tag:reinforcement-learning", "custom_tag:rlvr", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27347406407}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T20:45:41.553663+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5068454", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -205,7 +204,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:24:28.551031+00:00", "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15008654192, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 41847485419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:24:03.459331+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5154909", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T12:46:43.248987+00:00", "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780116, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780116}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-29T04:43:16.386995+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5163154", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-29T13:07:44.544808+00:00", "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780116, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780116}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-29T05:00:42.482777+00:00", "targetGpu": "MetaX_c-500", "taskId": "5163384", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T13:18:15.544758+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-29T05:17:59.663198+00:00", "targetGpu": "Vastai_va16", "taskId": "5163600", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-29T19:57:49.456558+00:00", "modelId": "IFM/K2-Horizon-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "48e1c6e7a33871d6d3101f837eae3cb6ea059723ae10471e3868971f0c6c8603", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9573964160, "estimatedRequiredGiB": 59.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 53374659671, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53374659671}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-29T11:50:55.455103+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5169654", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-30T00:34:13.067195+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171251735, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252373}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-29T16:33:38.851495+00:00", "targetGpu": "MetaX_c-500", "taskId": "5173419", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-30T00:53:38.455150+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171251735, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252373}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-29T16:49:54.151259+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5173704", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1019,7 +1017,6 @@
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T02:42:53.537287+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T18:41:25.446286+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5765199", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:09:41.435018+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:08:37.639861+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766311", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:09:41.435054+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:08:37.652020+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766310", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:16:23.645889+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:16:08.741643+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766395", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:16:23.645912+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:16:08.740412+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766394", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T04:52:41.033094+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:52:23.183394+00:00", "targetGpu": "MetaX_c-500", "taskId": "5766836", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T04:58:45.843576+00:00", "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064344108, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064344108}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:58:11.067331+00:00", "targetGpu": "Biren_166m", "taskId": "5766914", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user