state: generation 5193 (cycle)
This commit is contained in:
@@ -1311,7 +1311,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T13:54:39.983458+00:00",
|
||||
"generatedAt": "2026-09-10T13:57:27.577947+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 369,
|
||||
"listingErrors": 370,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 7,
|
||||
"nextAccountIndex": 8,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T13:54:39.958512+00:00",
|
||||
"updatedAt": "2026-09-10T13:57:27.551446+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T13:52:47.816020+00:00",
|
||||
"generatedAt": "2026-09-10T13:55:47.893790+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T13:47:00.396636+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:47:00.004718+00:00",
|
||||
"generatedAt": "2026-09-10T13:55:41.106863+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:55:40.785159+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1492,30 +1492,30 @@
|
||||
"unresolvedFailureCount": 31
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
"decisionFailureRate": 0.9615,
|
||||
"decisionSuccessRate": 0.0385,
|
||||
"decisionTotal": 26,
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 26,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.9873,
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.9875,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0127,
|
||||
"successRate": 0.0125,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 79,
|
||||
"total": 80,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -1905,29 +1905,29 @@
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 43,
|
||||
"decisionFailureRate": 0.9773,
|
||||
"decisionSuccessRate": 0.0227,
|
||||
"decisionTotal": 44,
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.9778,
|
||||
"decisionSuccessRate": 0.0222,
|
||||
"decisionTotal": 45,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 24,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 59,
|
||||
"failureRate": 0.9833,
|
||||
"failureCount": 60,
|
||||
"failureRate": 0.9836,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0167,
|
||||
"successRate": 0.0164,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 60,
|
||||
"total": 61,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2291,13 +2291,13 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 125,
|
||||
"decisionFailureRate": 0.7225,
|
||||
"decisionSuccessRate": 0.2775,
|
||||
"decisionTotal": 173,
|
||||
"attributableFailureCount": 126,
|
||||
"decisionFailureRate": 0.7241,
|
||||
"decisionSuccessRate": 0.2759,
|
||||
"decisionTotal": 174,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 117,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 26,
|
||||
@@ -2305,24 +2305,24 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 971,
|
||||
"failureCount": 972,
|
||||
"failureRate": 0.9529,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0471,
|
||||
"total": 1019,
|
||||
"total": 1020,
|
||||
"unresolvedFailureCount": 846
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 237,
|
||||
"attributableFailureCount": 238,
|
||||
"decisionFailureRate": 0.9958,
|
||||
"decisionSuccessRate": 0.0042,
|
||||
"decisionTotal": 238,
|
||||
"decisionTotal": 239,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 172,
|
||||
"backend_operator": 30,
|
||||
"backend_operator": 31,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 18,
|
||||
@@ -2332,14 +2332,14 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 434,
|
||||
"failureCount": 435,
|
||||
"failureRate": 0.9977,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0023,
|
||||
"total": 435,
|
||||
"total": 436,
|
||||
"unresolvedFailureCount": 196
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T13:47:00.392689+00:00",
|
||||
"generatedAt": "2026-09-10T13:55:41.102757+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2494,27 +2494,27 @@
|
||||
"unresolvedFailureCount": 218
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"attributableFailureCount": 27,
|
||||
"decisionFailureRate": 0.9643,
|
||||
"decisionSuccessRate": 0.0357,
|
||||
"decisionTotal": 28,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 26,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.9875,
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9877,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0125,
|
||||
"total": 80,
|
||||
"successRate": 0.0123,
|
||||
"total": 81,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -2650,27 +2650,27 @@
|
||||
"unresolvedFailureCount": 86
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 43,
|
||||
"decisionFailureRate": 0.8113,
|
||||
"decisionSuccessRate": 0.1887,
|
||||
"decisionTotal": 53,
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.8148,
|
||||
"decisionSuccessRate": 0.1852,
|
||||
"decisionTotal": 54,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 24,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 17,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 115,
|
||||
"failureRate": 0.92,
|
||||
"failureCount": 116,
|
||||
"failureRate": 0.9206,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.08,
|
||||
"total": 125,
|
||||
"successRate": 0.0794,
|
||||
"total": 126,
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -3729,14 +3729,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 6,
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 6
|
||||
"backend_operator": 7
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "starcoder2",
|
||||
@@ -3748,7 +3748,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
|
||||
@@ -4084,31 +4084,31 @@
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 5,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8571,
|
||||
"decisionSuccessRate": 0.1429,
|
||||
"decisionTotal": 7,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureRate": 0.9412,
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.9444,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T11:57:54.623286+00:00",
|
||||
"lastTerminalAt": "2026-09-10T13:55:40.785120+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0588,
|
||||
"successRate": 0.0556,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -6715,14 +6715,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|31": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
"backend_operator": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
@@ -6735,7 +6735,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|32": {
|
||||
@@ -7099,16 +7099,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1592,
|
||||
"totalRecords": 1679,
|
||||
"terminalRecords": 1594,
|
||||
"totalRecords": 1681,
|
||||
"totals": {
|
||||
"attributableFailureCount": 416,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 467,
|
||||
"attributableFailureCount": 418,
|
||||
"decisionFailureRate": 0.8913,
|
||||
"decisionSuccessRate": 0.1087,
|
||||
"decisionTotal": 469,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 351,
|
||||
"backend_operator": 36,
|
||||
"backend_operator": 38,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 48,
|
||||
@@ -7119,21 +7119,21 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1541,
|
||||
"failureCount": 1543,
|
||||
"failureRate": 0.968,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.032,
|
||||
"total": 1592,
|
||||
"total": 1594,
|
||||
"unresolvedFailureCount": 1122
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -7141,7 +7141,7 @@
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_mrv-100|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|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"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。",
|
||||
@@ -7162,6 +7162,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1679,
|
||||
"summarizedRecords": 1681,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T13:55:40.785120+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:47:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610380", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"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": "", "lastSyncTime": "2026-09-10T13:30:05.632388+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496944", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"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": "", "lastSyncTime": "2026-09-10T13:23:06.708419+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:19:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496965", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T12:40:42.405633+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523210", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-08T03:04:50.903997+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T02:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4478885", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-09-08T02:44:16.604700+00:00", "modelId": "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T02:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "3987363", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T02:44:16.604726+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T02:41:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079153", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-08T02:11:07.432317+00:00", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T02:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133668", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "7c6267f3ddada20f8d3359bbb3854103d0e38cc8a09ab42c3e6f8dffca1c711a",
|
||||
".modelhub_state/architecture_history_backfill.json": "5231613858db3e5b36dcffd95abe169c1d695f373c3df3b7b465030d9dff7b66",
|
||||
".modelhub_state/market_intelligence.json": "37243df3b0eab1b9f25fb9f5d35ce8ddce3063ed7a5d30859297be77b5e677c8",
|
||||
".modelhub_state/official_capabilities.json": "2260d5980ff631a7df3250d13e6d61e2f42657a8069a974bcbb95edde9ebb8a0",
|
||||
".modelhub_state/outcome_checkpoint.json": "ee6bf05cac27bbd86eaa99f42b29507ae81195ad52b29e1f006bc7f4002cb254",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "bbdebfddb812e94c70b5d21231810af08436eb97e3454ddbc874eaa12138c58e",
|
||||
".modelhub_state/architecture_history_backfill.json": "4a3f23cda3477c7c2d0424b0741dc28377900d6b2635a7c98c63d6421dec6ac4",
|
||||
".modelhub_state/market_intelligence.json": "e1fa81f8363ea7816cfba08b6dac2ee481c518982ae492afdcf71f34c6e3a7b0",
|
||||
".modelhub_state/official_capabilities.json": "014bf8545743ee2375b30b880d4bf95686eb0cd210ccb49a93a1946b9df6e706",
|
||||
".modelhub_state/outcome_checkpoint.json": "d79ff94dd9fec12a5a24b8e266d0495598f6e28e81ba9e6cc1a21f22ed64138e",
|
||||
".modelhub_state/queue_cleanup_latest.json": "a596175137b8adfa14ee62a71c9a7bc915b25b1d8f0f57451a25c2e257396039",
|
||||
".modelhub_state/recent_outcomes.jsonl": "70ae2484ad7f3eeeca2205d11f4f04dc6fa97c64a650c1441e1d098841fe42e8",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "ac0cf05c214f0db2240819a2929b9c30b5249dc60de76cd77bea705da7eaabb6",
|
||||
".modelhub_state/recovery_intents.jsonl": "8f7664e0bb67360338a0614206703c288f209f9bed6e89c6d3ddb46e06b5ee6f",
|
||||
".modelhub_state/recent_outcomes.jsonl": "4da993fbb735ac37a77285e48f6ba2899ccd6e04775137b67015e8410168648a",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "c551a60f33b78b757782cc1acc4b7b786b7c0af1ab1cafddfa843110a2d88af4",
|
||||
".modelhub_state/recovery_intents.jsonl": "beaf75738326554b6ef3611c203f97faff8bbfa9bb16639bae0d1fbefdc8cb06",
|
||||
".modelhub_state/routing_intelligence.json": "5d6f745d56b69f23b3cfad9a5bd343a36b4b56bb8553dea7bb11d7a023d2b106",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "0f6a07019717c0581f3778638e348ad7721b822cd5395d9c5be97392d420b0a5",
|
||||
"outcomes/submissions.jsonl": "3157c87f332ecd614a2b5bb9887f100742c03d4d5595ab33c5649bc08d380f1e"
|
||||
"outcomes/submissions.jsonl": "dd8f82424fd7e255cff1d5e84f475fe0d3159d86a48ce6f10bf1472ec312a95d"
|
||||
},
|
||||
"generation": 5192,
|
||||
"generation": 5193,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T13:54:40.120956+00:00",
|
||||
"updatedAt": "2026-09-10T13:57:28.475327+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
@@ -120,7 +120,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913909+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 9093198689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.097444+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648145", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "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": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913797+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"backend_operator": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T10:14:38.509276+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.186785+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648143", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:15:28.523439+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0dce7c4be445254429760db90c7969177ecdca460563778d8b3371a37cc1a50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523328+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.114152+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649233", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523422+00:00", "modelId": "douyamv/Qwen3.8-27B-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28178526992, "estimatedRequiredGiB": 31.518, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 28201576294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:vllm", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 28201576294}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.110104+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649235", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -550,8 +549,8 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004700+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.454183+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753713", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004708+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.451335+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753714", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004674+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.452554+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753715", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T05:47:10.742578+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753833", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1764a9124cd000c7904ba9cee10ecdf5f9bfd4e65fc6896e0120a683f5e606e3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:55:40.785136+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:47:10.742578+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753833", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T13:55:40.785159+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1764a9124cd000c7904ba9cee10ecdf5f9bfd4e65fc6896e0120a683f5e606e3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T05:55:59.442486+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754066", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T05:55:59.435840+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T05:55:59.437900+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user