state: generation 5961 (cycle)
This commit is contained in:
@@ -1307,7 +1307,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T01:24:56.571209+00:00",
|
||||
"generatedAt": "2026-09-12T01:27:59.007804+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 427,
|
||||
"listingErrors": 428,
|
||||
"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": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-12T01:24:56.548153+00:00",
|
||||
"updatedAt": "2026-09-12T01:27:58.984862+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T01:23:05.953415+00:00",
|
||||
"generatedAt": "2026-09-12T01:26:04.975523+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T00:52:00.246547+00:00",
|
||||
"lastSyncTime": "2026-09-12T00:52:00.210563+00:00",
|
||||
"generatedAt": "2026-09-12T01:25:57.550819+00:00",
|
||||
"lastSyncTime": "2026-09-12T01:25:57.322172+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1762,18 +1762,18 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"attributableFailureCount": 16,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 15,
|
||||
"decisionTotal": 16,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"model_load": 3,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 22,
|
||||
"failureCount": 23,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1783,34 +1783,34 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 22,
|
||||
"total": 23,
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 87,
|
||||
"decisionFailureRate": 0.8788,
|
||||
"decisionSuccessRate": 0.1212,
|
||||
"decisionTotal": 99,
|
||||
"attributableFailureCount": 88,
|
||||
"decisionFailureRate": 0.88,
|
||||
"decisionSuccessRate": 0.12,
|
||||
"decisionTotal": 100,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19,
|
||||
"framework_architecture_unsupported": 49,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 37,
|
||||
"model_load": 38,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 156,
|
||||
"failureRate": 0.9286,
|
||||
"failureCount": 157,
|
||||
"failureRate": 0.929,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 12,
|
||||
"successRate": 0.0714,
|
||||
"successRate": 0.071,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 168,
|
||||
"total": 169,
|
||||
"unresolvedFailureCount": 68
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
@@ -2311,40 +2311,40 @@
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 141,
|
||||
"decisionFailureRate": 0.7344,
|
||||
"decisionSuccessRate": 0.2656,
|
||||
"decisionTotal": 192,
|
||||
"attributableFailureCount": 142,
|
||||
"decisionFailureRate": 0.7358,
|
||||
"decisionSuccessRate": 0.2642,
|
||||
"decisionTotal": 193,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 130,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 90,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 39,
|
||||
"model_load": 40,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 59,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1004,
|
||||
"failureCount": 1005,
|
||||
"failureRate": 0.9517,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0483,
|
||||
"total": 1055,
|
||||
"total": 1056,
|
||||
"unresolvedFailureCount": 862
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 244,
|
||||
"attributableFailureCount": 245,
|
||||
"decisionFailureRate": 0.9879,
|
||||
"decisionSuccessRate": 0.0121,
|
||||
"decisionTotal": 247,
|
||||
"decisionTotal": 248,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 171,
|
||||
"framework_architecture_unsupported": 172,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 19,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2353,14 +2353,14 @@
|
||||
"tokenizer_compatibility": 4,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 464,
|
||||
"failureCount": 465,
|
||||
"failureRate": 0.9936,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0064,
|
||||
"total": 467,
|
||||
"total": 468,
|
||||
"unresolvedFailureCount": 219
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2464,7 +2464,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T00:52:00.242533+00:00",
|
||||
"generatedAt": "2026-09-12T01:25:57.546677+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2603,51 +2603,51 @@
|
||||
"unresolvedFailureCount": 27
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"attributableFailureCount": 20,
|
||||
"decisionFailureRate": 0.7143,
|
||||
"decisionSuccessRate": 0.2857,
|
||||
"decisionTotal": 28,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 0.7241,
|
||||
"decisionSuccessRate": 0.2759,
|
||||
"decisionTotal": 29,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"backend_operator": 5,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"framework_architecture_unsupported": 10,
|
||||
"model_load": 4,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 64,
|
||||
"failureRate": 0.8889,
|
||||
"failureCount": 65,
|
||||
"failureRate": 0.8904,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 8,
|
||||
"successRate": 0.1111,
|
||||
"total": 72,
|
||||
"successRate": 0.1096,
|
||||
"total": 73,
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 88,
|
||||
"decisionFailureRate": 0.88,
|
||||
"decisionSuccessRate": 0.12,
|
||||
"decisionTotal": 100,
|
||||
"attributableFailureCount": 89,
|
||||
"decisionFailureRate": 0.8812,
|
||||
"decisionSuccessRate": 0.1188,
|
||||
"decisionTotal": 101,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19,
|
||||
"framework_architecture_unsupported": 49,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 38,
|
||||
"model_load": 39,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 157,
|
||||
"failureRate": 0.929,
|
||||
"failureCount": 158,
|
||||
"failureRate": 0.9294,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 12,
|
||||
"successRate": 0.071,
|
||||
"total": 169,
|
||||
"successRate": 0.0706,
|
||||
"total": 170,
|
||||
"unresolvedFailureCount": 68
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -4303,22 +4303,22 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 2
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-11T20:03:23.495341+00:00",
|
||||
"lastTerminalAt": "2026-09-12T01:25:57.322124+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4326,30 +4326,29 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"consecutiveFailures": 0,
|
||||
"attributableFailureCount": 16,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8824,
|
||||
"decisionSuccessRate": 0.1176,
|
||||
"decisionTotal": 17,
|
||||
"decisionFailureRate": 0.8889,
|
||||
"decisionSuccessRate": 0.1111,
|
||||
"decisionTotal": 18,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 13,
|
||||
"platform_infrastructure": 1
|
||||
"model_load": 14
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
|
||||
"lastTerminalAt": "2026-09-12T00:52:00.210542+00:00",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T01:25:57.322172+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
@@ -4365,9 +4364,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4379,8 +4378,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7055,19 +7054,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1670,
|
||||
"totalRecords": 1757,
|
||||
"terminalRecords": 1672,
|
||||
"totalRecords": 1759,
|
||||
"totals": {
|
||||
"attributableFailureCount": 442,
|
||||
"decisionFailureRate": 0.8876,
|
||||
"decisionSuccessRate": 0.1124,
|
||||
"decisionTotal": 498,
|
||||
"attributableFailureCount": 444,
|
||||
"decisionFailureRate": 0.888,
|
||||
"decisionSuccessRate": 0.112,
|
||||
"decisionTotal": 500,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 394,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 276,
|
||||
"framework_architecture_unsupported": 277,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 62,
|
||||
"model_load": 63,
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 6,
|
||||
@@ -7075,31 +7074,30 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1614,
|
||||
"failureCount": 1616,
|
||||
"failureRate": 0.9665,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 56,
|
||||
"successRate": 0.0335,
|
||||
"total": 1670,
|
||||
"total": 1672,
|
||||
"unresolvedFailureCount": 1168
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"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-x4|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 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7114,10 +7112,11 @@
|
||||
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|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 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1757,
|
||||
"summarizedRecords": 1759,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
{"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": "2026-09-12T01:25:57.322124+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T01:25:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079965", "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": "2026-09-12T01:25:57.322172+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T01:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523213", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T00:52:00.210542+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T00:49:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523319", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207568+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079945", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207605+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079258", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -296,5 +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": "2026-09-08T12:11:42.795288+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:07:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080027", "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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T12:11:42.795279+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080026", "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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T11:42:26.289451+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:35:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4007714", "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": "2026-09-08T11:42:26.289433+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T11:25:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4483789", "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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T11:18:26.601995+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079157", "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": "498ac589909afc42fa6aa4823af1fd21384f65fac07aa450a3fe21b69976334c",
|
||||
".modelhub_state/architecture_history_backfill.json": "585895a131c82df56b5d5d08a7330094963dda1b4e464bce64b3c3762c97bbc4",
|
||||
".modelhub_state/market_intelligence.json": "1b83c923379bb17d568613591094747c7967b0acd589ce808c127f5511e43467",
|
||||
".modelhub_state/official_capabilities.json": "5583a94442366fd071b02e83b8e7f34b6599b396016f82a72e5889cf13524f1a",
|
||||
".modelhub_state/outcome_checkpoint.json": "4b872b4b87cf53ada4a85e829cba0ed794080e295554f5086ff1686be646196c",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2fc984ca6657e9019c08bb928c5a7d86737350c00353d46df6657908c992afe6",
|
||||
".modelhub_state/architecture_history_backfill.json": "37af17c3bbeb2303353c83bca3c434e8815053f04ffa942671b1466ce5efc26a",
|
||||
".modelhub_state/market_intelligence.json": "c15838bf5cc549ef4f65fb697c639ae681dea88e1018bb2fdf14167d53011a6d",
|
||||
".modelhub_state/official_capabilities.json": "02ace12b5c08b0864a467074527df3c53f8275599d4f3b2de4ba88e42955a5b0",
|
||||
".modelhub_state/outcome_checkpoint.json": "cd5c8e675da713486a5e792c7abed79f8050b95b6a45ebea31a11fe897ba3f6a",
|
||||
".modelhub_state/queue_cleanup_latest.json": "4dfcc8b80b2419e5225f1190630781005a36a05d5bae67488c08a65216f950fb",
|
||||
".modelhub_state/recent_outcomes.jsonl": "edba5fcdb79666ed8098b98a179a624eeacdd10ae2bff79ea709ff78c7657c8e",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "1d7e33d6838b8451169259bfdea7518f0ac2515dec813a57a67df17215c6c342",
|
||||
".modelhub_state/recovery_intents.jsonl": "63481b5ba702d492f0edcf993d1fa61061dece79a35a1cb384e968fc72b44bf2",
|
||||
".modelhub_state/recent_outcomes.jsonl": "22c3f5e187c9e20b62ae20d30f1bc0acbbc6493d2e27a992ab5c1e90bb781217",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "966c2238b3c3b124d126a949630369253167b824941fe66bf77b09d312cc233b",
|
||||
".modelhub_state/recovery_intents.jsonl": "32e414f34d6b64b95e32e4a71a9e6fed32256820bed6222effb52d5808a596e6",
|
||||
".modelhub_state/routing_intelligence.json": "316b7d02e32cf2dd3f7c0ca452f58d571a371863ac4d1c1b5193456035ce3a53",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "8abcf838f382e71b9140db2901b93972a33b043c4c67a56473d00af9ccd9be3c",
|
||||
"outcomes/submissions.jsonl": "76f5b4680a6d525bbe4bac93badb9e9545b2117a5a448366a6110d75cf16c418"
|
||||
"outcomes/submissions.jsonl": "b6311bfa5b46c651c1199546edb97c9eda7a3fd179b18e4efe51c478fedfefe5"
|
||||
},
|
||||
"generation": 5960,
|
||||
"generation": 5961,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-12T01:24:56.645170+00:00",
|
||||
"updatedAt": "2026-09-12T01:27:59.625150+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
@@ -616,7 +616,7 @@
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-12T01:00:32.503357+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:54:32.845710+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4783202", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T01:09:07.406128+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T17:01:11.403970+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4783339", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-12T01:18:10.999715+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T17:12:06.612979+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4783476", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T17:22:24.744587+00:00", "targetGpu": "MetaX_c-500", "taskId": "4783634", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T01:25:57.322160+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T17:22:24.744587+00:00", "targetGpu": "MetaX_c-500", "taskId": "4783634", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "6647f6920340e837cb19ab6ec8bc02c4d5d8cebe4d720e359319e40aa1ebaf79", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T18:18:29.685555+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4784429", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T18:18:29.687478+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4784430", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-11T18:51:22.774816+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4784981", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user