state: generation 6735 (cycle)
This commit is contained in:
@@ -1475,7 +1475,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T13:16:29.807791+00:00",
|
||||
"generatedAt": "2026-09-13T13:19:22.317229+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 74,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 487,
|
||||
"listingErrors": 488,
|
||||
"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": 10,
|
||||
"nextAccountIndex": 11,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-13T13:16:29.778608+00:00",
|
||||
"updatedAt": "2026-09-13T13:19:22.293499+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T13:14:45.107106+00:00",
|
||||
"generatedAt": "2026-09-13T13:17:40.477350+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T11:04:49.047170+00:00",
|
||||
"lastSyncTime": "2026-09-13T11:04:48.812977+00:00",
|
||||
"generatedAt": "2026-09-13T13:17:31.378518+00:00",
|
||||
"lastSyncTime": "2026-09-13T13:17:31.149592+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1656,30 +1656,30 @@
|
||||
"unresolvedFailureCount": 35
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.9667,
|
||||
"decisionSuccessRate": 0.0333,
|
||||
"decisionTotal": 30,
|
||||
"attributableFailureCount": 30,
|
||||
"decisionFailureRate": 0.9677,
|
||||
"decisionSuccessRate": 0.0323,
|
||||
"decisionTotal": 31,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 84,
|
||||
"failureRate": 0.9882,
|
||||
"failureCount": 85,
|
||||
"failureRate": 0.9884,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0118,
|
||||
"successRate": 0.0116,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 85,
|
||||
"total": 86,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -2484,14 +2484,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 152,
|
||||
"decisionFailureRate": 0.7379,
|
||||
"decisionSuccessRate": 0.2621,
|
||||
"decisionTotal": 206,
|
||||
"attributableFailureCount": 153,
|
||||
"decisionFailureRate": 0.7391,
|
||||
"decisionSuccessRate": 0.2609,
|
||||
"decisionTotal": 207,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 142,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 97,
|
||||
"framework_architecture_unsupported": 98,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 43,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2499,14 +2499,14 @@
|
||||
"参数/模板问题": 61,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1029,
|
||||
"failureRate": 0.9501,
|
||||
"failureCount": 1030,
|
||||
"failureRate": 0.9502,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 54,
|
||||
"successRate": 0.0499,
|
||||
"total": 1083,
|
||||
"successRate": 0.0498,
|
||||
"total": 1084,
|
||||
"unresolvedFailureCount": 876
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2638,7 +2638,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T11:04:49.041570+00:00",
|
||||
"generatedAt": "2026-09-13T13:17:31.373858+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2689,27 +2689,27 @@
|
||||
"unresolvedFailureCount": 223
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 32,
|
||||
"decisionFailureRate": 0.9697,
|
||||
"decisionSuccessRate": 0.0303,
|
||||
"decisionTotal": 33,
|
||||
"attributableFailureCount": 33,
|
||||
"decisionFailureRate": 0.9706,
|
||||
"decisionSuccessRate": 0.0294,
|
||||
"decisionTotal": 34,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 28,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 87,
|
||||
"failureRate": 0.9886,
|
||||
"failureCount": 88,
|
||||
"failureRate": 0.9888,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0114,
|
||||
"total": 88,
|
||||
"successRate": 0.0112,
|
||||
"total": 89,
|
||||
"unresolvedFailureCount": 55
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -4582,23 +4582,23 @@
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"attributableFailureCount": 10,
|
||||
"consecutiveFailures": 10,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 19,
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-13T06:31:13.105179+00:00",
|
||||
"lastTerminalAt": "2026-09-13T13:17:31.149556+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4606,7 +4606,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 19,
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -7507,17 +7507,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1772,
|
||||
"totalRecords": 1859,
|
||||
"terminalRecords": 1773,
|
||||
"totalRecords": 1860,
|
||||
"totals": {
|
||||
"attributableFailureCount": 517,
|
||||
"decisionFailureRate": 0.8976,
|
||||
"decisionSuccessRate": 0.1024,
|
||||
"decisionTotal": 576,
|
||||
"attributableFailureCount": 518,
|
||||
"decisionFailureRate": 0.8977,
|
||||
"decisionSuccessRate": 0.1023,
|
||||
"decisionTotal": 577,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 416,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 326,
|
||||
"framework_architecture_unsupported": 327,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 73,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7527,51 +7527,51 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1713,
|
||||
"failureCount": 1714,
|
||||
"failureRate": 0.9667,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 59,
|
||||
"successRate": 0.0333,
|
||||
"total": 1772,
|
||||
"total": 1773,
|
||||
"unresolvedFailureCount": 1192
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 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 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 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 Vastai_va16 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 Cambricon_mlu-370-x8 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 Biren_166m 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 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。",
|
||||
"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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_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 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-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 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm-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|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。",
|
||||
"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 Ascend_910-b4 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。",
|
||||
"组合 Biren_166m|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 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 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。",
|
||||
"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 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 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 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 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 Sunrise_pt-200-x1|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。",
|
||||
"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 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 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 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 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。",
|
||||
"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。",
|
||||
"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 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 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 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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1859,
|
||||
"summarizedRecords": 1860,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"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": "2026-09-13T13:17:31.149556+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T13:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4349465", "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": "2026-09-13T10:05:37.717736+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:59:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560059", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T09:40:23.641563+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4557415", "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", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-13T08:31:12.943798+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T08:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609080", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T14:59:28.333305+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T14:59:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477956", "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"], "framework": "", "lastSyncTime": "2026-09-09T14:59:28.333331+00:00", "modelId": "ornith-ai/Ornith-1.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T14:55:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332980", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T16:44:50.902809+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634920, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "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": "2026-09-09T12:08:11.431365+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T12:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080603", "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
@@ -147,7 +147,6 @@
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-06T00:30:40.392742+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657912", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "submitTime": "2026-09-06T00:30:40.349157+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657906", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-06T00:30:40.350638+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657905", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "submitTime": "2026-09-06T00:30:40.388241+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657909", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-2.9B-20260805", "modelId": "RWKV/RWKV7-2.9B-20260805", "submitTime": "2026-09-06T00:51:47.515580+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4658219", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-06T02:23:39.684428+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659269", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-06T02:23:39.690219+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659268", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
|
||||
|
||||
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "52bcb4fd1a77956f1e6f2f72b5a4f3a8d5b7955dd178ede9386b3aedbd107eb9",
|
||||
".modelhub_state/architecture_history_backfill.json": "046f348c54e3f028f87ec7f4fffec4eff0888f9f50a8f0671e9a870e94ac3153",
|
||||
".modelhub_state/market_intelligence.json": "216c4ab8a38c50430dde74d53b613651a18cf917064d893c91c9bece3a4c96ee",
|
||||
".modelhub_state/official_capabilities.json": "09dd2e4aca63bb3c7e983144541dafa2515619050c0d39c9ad415fe3ac9d7da0",
|
||||
".modelhub_state/outcome_checkpoint.json": "7805a56c300648994f07cd51eabc9f83a6d63d807bc0341a340b800fb8979ba6",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "9076c4a586e0e51539254055a7ffa23e6bdbdb8589d6be7cc2303753ffea5da7",
|
||||
".modelhub_state/architecture_history_backfill.json": "646f953cf8a1555475d63294669237ca82c3c526843e0735f89717dc9c8b96e4",
|
||||
".modelhub_state/market_intelligence.json": "a26e0eed9ba302b2347ef4abb9106fed107fd567354ba465d91fe8a006f1ada3",
|
||||
".modelhub_state/official_capabilities.json": "ff527f81cd95f8624dbaa86bc0a8fd9dfb46afab67c99ff6db26448c958a6beb",
|
||||
".modelhub_state/outcome_checkpoint.json": "23361a1678b2f670ba8d73c122ca661e8307554a440e764043a328757822bdd5",
|
||||
".modelhub_state/queue_cleanup_latest.json": "5b0dc54b913434ae76ea5833cabfa7c00f3e8191ff58197626eeea4fbe7a9af1",
|
||||
".modelhub_state/recent_outcomes.jsonl": "37cdee1c5f1b3c8b6573da6796fd6b89e122be93b75484612709af6cee5c4776",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "1fd0553ee32a4d521233512bfab11f6c757cb86e4106a0d6aaaff497716d2b59",
|
||||
".modelhub_state/recovery_intents.jsonl": "789fe568de7d074eb903074be8fda6281fbb9261596afdaecbe8c4a8fc8319b5",
|
||||
".modelhub_state/recent_outcomes.jsonl": "c85b22806f044efb78722e4de0711025ade9a6034b8801cf1e294aaf87849ff3",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "d2132027ce0c3e1fa579b3e74a682b73e36d8d9692fcb634c5b9e3f1ab0d3e6c",
|
||||
".modelhub_state/recovery_intents.jsonl": "33b22602598dc609a4e015f34af31394024d93e945d2381f16451843b99c5aba",
|
||||
".modelhub_state/routing_intelligence.json": "c676612ee86c9cadeb60464165c636857dacc1827858bd254c92284a746c1c02",
|
||||
".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263",
|
||||
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
|
||||
"ledger/submissions.jsonl": "5108d21ea31ef0f973375226630f4338b52c814fe2d917e65b43821da9f3fb69",
|
||||
"outcomes/submissions.jsonl": "2cfd0ccbf51d955a0ebcb01d37bc740095cadff28173d3161dafb94127b22c6d"
|
||||
"ledger/submissions.jsonl": "43901660d4dbe64676c5256591ca704f3699fc6b1b5a96361d9b9e6dbf314289",
|
||||
"outcomes/submissions.jsonl": "4554493a6847021287a119b1bd32d3bfe33aeb995dcc9126b996414d3dd4fedd"
|
||||
},
|
||||
"generation": 6734,
|
||||
"generation": 6735,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-13T13:16:29.886962+00:00",
|
||||
"updatedAt": "2026-09-13T13:19:22.995984+00:00",
|
||||
"writerId": "69701e73196b4ac2b3fad0f412335168"
|
||||
}
|
||||
|
||||
@@ -628,7 +628,7 @@
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-13T12:45:24.349544+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "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": "2026-09-13T04:41:29.963690+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817349", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-13T12:45:24.349554+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 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": "2026-09-13T04:41:29.962163+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817348", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:00:14.407763+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:51:53.062775+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4817454", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T05:10:44.864092+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4817675", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:17:31.149592+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:10:44.864092+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4817675", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T05:29:18.044774+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4817992", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T05:34:18.006195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4818284", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T05:44:36.060924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4818885", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user