state: generation 6404 (cycle)
This commit is contained in:
@@ -1429,7 +1429,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-12T22:59:13.141133+00:00",
|
"generatedAt": "2026-09-12T23:02:09.989583+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 72,
|
"activeBlockCount": 72,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
@@ -83,7 +83,7 @@
|
|||||||
"8": {
|
"8": {
|
||||||
"complete": false,
|
"complete": false,
|
||||||
"lastError": "ModelHubAPIError: 系统错误",
|
"lastError": "ModelHubAPIError: 系统错误",
|
||||||
"listingErrors": 462,
|
"listingErrors": 463,
|
||||||
"nextPage": 1,
|
"nextPage": 1,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"uniqueRecords": 0
|
"uniqueRecords": 0
|
||||||
@@ -102,12 +102,12 @@
|
|||||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"failureLogsInspected": 0,
|
"failureLogsInspected": 0,
|
||||||
"mode": "incremental_decision_only",
|
"mode": "incremental_decision_only",
|
||||||
"nextAccountIndex": 8,
|
"nextAccountIndex": 9,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"seenTaskIds": [],
|
"seenTaskIds": [],
|
||||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"terminalRecords": 0,
|
"terminalRecords": 0,
|
||||||
"uniqueRecords": 0,
|
"uniqueRecords": 0,
|
||||||
"updatedAt": "2026-09-12T22:59:13.116866+00:00",
|
"updatedAt": "2026-09-12T23:02:09.965118+00:00",
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -416,7 +416,7 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-09-12T22:57:37.619793+00:00",
|
"generatedAt": "2026-09-12T23:00:20.706858+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"available": true,
|
"available": true,
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-09-12T22:34:15.755489+00:00",
|
"generatedAt": "2026-09-12T23:00:14.027433+00:00",
|
||||||
"lastSyncTime": "2026-09-12T22:34:15.509071+00:00",
|
"lastSyncTime": "2026-09-12T23:00:13.841305+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -1964,11 +1964,11 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 1,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 34,
|
"ambiguous_runtime": 35,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"验证失败": 22
|
"验证失败": 22
|
||||||
},
|
},
|
||||||
"failureCount": 57,
|
"failureCount": 58,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -1978,8 +1978,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Kunlunxin_p-800",
|
"targetGpu": "Kunlunxin_p-800",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 57,
|
"total": 58,
|
||||||
"unresolvedFailureCount": 56
|
"unresolvedFailureCount": 57
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800|unknown|visual-multi-modal": {
|
"Kunlunxin_p-800|unknown|visual-multi-modal": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -2442,7 +2442,7 @@
|
|||||||
"decisionSuccessRate": 0.2624,
|
"decisionSuccessRate": 0.2624,
|
||||||
"decisionTotal": 202,
|
"decisionTotal": 202,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 136,
|
"ambiguous_runtime": 137,
|
||||||
"backend_operator": 4,
|
"backend_operator": 4,
|
||||||
"framework_architecture_unsupported": 94,
|
"framework_architecture_unsupported": 94,
|
||||||
"memory_capacity": 5,
|
"memory_capacity": 5,
|
||||||
@@ -2452,15 +2452,15 @@
|
|||||||
"参数/模板问题": 59,
|
"参数/模板问题": 59,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 1018,
|
"failureCount": 1019,
|
||||||
"failureRate": 0.9505,
|
"failureRate": 0.9506,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 53,
|
"successCount": 53,
|
||||||
"successRate": 0.0495,
|
"successRate": 0.0494,
|
||||||
"total": 1071,
|
"total": 1072,
|
||||||
"unresolvedFailureCount": 868
|
"unresolvedFailureCount": 869
|
||||||
},
|
},
|
||||||
"vllm": {
|
"vllm": {
|
||||||
"attributableFailureCount": 282,
|
"attributableFailureCount": 282,
|
||||||
@@ -2591,7 +2591,7 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-12T22:34:15.749897+00:00",
|
"generatedAt": "2026-09-12T23:00:14.021225+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 30,
|
"attributableFailureCount": 30,
|
||||||
@@ -2784,20 +2784,20 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 1,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 68,
|
"ambiguous_runtime": 69,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"参数/模板问题": 1,
|
"参数/模板问题": 1,
|
||||||
"验证失败": 23
|
"验证失败": 23
|
||||||
},
|
},
|
||||||
"failureCount": 93,
|
"failureCount": 94,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 0,
|
"successCount": 0,
|
||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"total": 93,
|
"total": 94,
|
||||||
"unresolvedFailureCount": 92
|
"unresolvedFailureCount": 93
|
||||||
},
|
},
|
||||||
"MetaX_c-500": {
|
"MetaX_c-500": {
|
||||||
"attributableFailureCount": 52,
|
"attributableFailureCount": 52,
|
||||||
@@ -4636,13 +4636,13 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 5
|
"ambiguous_runtime": 6
|
||||||
},
|
},
|
||||||
"failureCount": 5,
|
"failureCount": 6,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
"lastTerminalAt": "2026-09-12T13:02:08.318677+00:00",
|
"lastTerminalAt": "2026-09-12T23:00:13.841305+00:00",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
@@ -4650,8 +4650,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Kunlunxin_p-800",
|
"targetGpu": "Kunlunxin_p-800",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 5,
|
"total": 6,
|
||||||
"unresolvedFailureCount": 5
|
"unresolvedFailureCount": 6
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -4661,9 +4661,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 4
|
"ambiguous_runtime": 3
|
||||||
},
|
},
|
||||||
"failureCount": 4,
|
"failureCount": 3,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -4675,8 +4675,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Kunlunxin_p-800",
|
"targetGpu": "Kunlunxin_p-800",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 4,
|
"total": 3,
|
||||||
"unresolvedFailureCount": 4
|
"unresolvedFailureCount": 3
|
||||||
},
|
},
|
||||||
"MetaX_c-500|vllm|text-generation": {
|
"MetaX_c-500|vllm|text-generation": {
|
||||||
"attributableFailureCount": 6,
|
"attributableFailureCount": 6,
|
||||||
@@ -4942,31 +4942,6 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"recentProfileCombinationStats": {
|
"recentProfileCombinationStats": {
|
||||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
|
|
||||||
"attributableFailureCount": 0,
|
|
||||||
"consecutiveFailures": 0,
|
|
||||||
"decisionFailureRate": 0.0,
|
|
||||||
"decisionSuccessRate": 0.0,
|
|
||||||
"decisionTotal": 0,
|
|
||||||
"failureBreakdown": {
|
|
||||||
"ambiguous_runtime": 1
|
|
||||||
},
|
|
||||||
"failureCount": 1,
|
|
||||||
"failureRate": 1.0,
|
|
||||||
"framework": "vllm_fix_tokenizer",
|
|
||||||
"lastTerminalAt": "2026-09-09T13:57:00.114030+00:00",
|
|
||||||
"modelType": "qwen3_5_mtp",
|
|
||||||
"pendingCount": 0,
|
|
||||||
"pendingRate": 0.0,
|
|
||||||
"platformFailureCount": 0,
|
|
||||||
"quantizationMethod": "none",
|
|
||||||
"successCount": 0,
|
|
||||||
"successRate": 0.0,
|
|
||||||
"targetGpu": "Kunlunxin_p-800",
|
|
||||||
"taskType": "text-generation",
|
|
||||||
"total": 1,
|
|
||||||
"unresolvedFailureCount": 1
|
|
||||||
},
|
|
||||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
|
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
"consecutiveFailures": 0,
|
"consecutiveFailures": 0,
|
||||||
@@ -7272,15 +7247,15 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 1741,
|
"terminalRecords": 1742,
|
||||||
"totalRecords": 1828,
|
"totalRecords": 1829,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 497,
|
"attributableFailureCount": 497,
|
||||||
"decisionFailureRate": 0.8955,
|
"decisionFailureRate": 0.8955,
|
||||||
"decisionSuccessRate": 0.1045,
|
"decisionSuccessRate": 0.1045,
|
||||||
"decisionTotal": 555,
|
"decisionTotal": 555,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 408,
|
"ambiguous_runtime": 409,
|
||||||
"backend_operator": 42,
|
"backend_operator": 42,
|
||||||
"framework_architecture_unsupported": 309,
|
"framework_architecture_unsupported": 309,
|
||||||
"memory_capacity": 11,
|
"memory_capacity": 11,
|
||||||
@@ -7292,21 +7267,20 @@
|
|||||||
"参数/模板问题": 101,
|
"参数/模板问题": 101,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 1683,
|
"failureCount": 1684,
|
||||||
"failureRate": 0.9667,
|
"failureRate": 0.9667,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 4,
|
"platformFailureCount": 4,
|
||||||
"successCount": 58,
|
"successCount": 58,
|
||||||
"successRate": 0.0333,
|
"successRate": 0.0333,
|
||||||
"total": 1741,
|
"total": 1742,
|
||||||
"unresolvedFailureCount": 1182
|
"unresolvedFailureCount": 1183
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
"GPU Ascend_910-b3 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 Ascend_910-b4 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 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 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 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_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||||
@@ -7315,6 +7289,7 @@
|
|||||||
"GPU MetaX_c-500 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 Biren_166m 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。",
|
"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。",
|
||||||
"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-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 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 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。",
|
||||||
@@ -7337,6 +7312,6 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 1828,
|
"summarizedRecords": 1829,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,3 +1,4 @@
|
|||||||
|
{"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": "2026-09-12T23:00:13.841305+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T22:55:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560062", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-12T22:34:15.509071+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T22:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4543802", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-12T22:34:15.509071+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T22:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4543802", "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", "lastSyncTime": "2026-09-12T21:39:57.012261+00:00", "modelId": "QuantTrio/KAT-Dev-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079182", "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", "lastSyncTime": "2026-09-12T21:39:57.012261+00:00", "modelId": "QuantTrio/KAT-Dev-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079182", "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": "2026-09-12T21:28:41.303467+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523212", "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": "2026-09-12T21:28:41.303467+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523212", "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": "2026-09-08T23:59:40.403464+00:00", "modelId": "RedHatAI/Qwen2.5-7B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080289", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T23:59:40.403464+00:00", "modelId": "RedHatAI/Qwen2.5-7B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080289", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T09:38:19.106782+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:52.084632+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729528", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T09:38:19.106782+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:52.084632+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729528", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:21:21.949441+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.998598+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729524", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:21:21.949441+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.998598+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729524", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T13:57:00.114030+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 225662258, "estimatedRequiredGiB": 0.282, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 252393272, "modelscopeLicense": "apache-2.0", "modelscopeParams": 79652352, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:mxfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 252393272}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.995104+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729526", "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",
|
"agentVersion": "2026.09.04.4",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "6745b376137a13343bb76d9dd390ebeed2304e3e3cfc818aac35833f2121e550",
|
".modelhub_state/architecture_compatibility_blacklist.json": "469af084a7add8e150bd379e459d41a25b35a9b8b804057ca15e5c40a5b5a009",
|
||||||
".modelhub_state/architecture_history_backfill.json": "4415fbb2d4d38f7c79fc13190e08b47a9179aff8a21c628886de93bbf3a2acdb",
|
".modelhub_state/architecture_history_backfill.json": "6d2f7cb8ad0c6cf1f0742011ad526a8fff0de53ec169c4de12361b15e9bda52a",
|
||||||
".modelhub_state/market_intelligence.json": "556fb9e8ea4b1480a63815605bc3cb1da2cd7262fca8095da697a1c20dfa93e0",
|
".modelhub_state/market_intelligence.json": "d685cd1a4b58d2238e6c1884f195a346ddf76a69774415e947a1790b3e29e8d7",
|
||||||
".modelhub_state/official_capabilities.json": "8ce995d768c0d14bdd49533fc228071c1ad77254f1628057c9f7b176910c1c74",
|
".modelhub_state/official_capabilities.json": "f4d5d45e76e2c29a410a8eaca1cd08571a6606a896808208a9e4d56a45cb5b73",
|
||||||
".modelhub_state/outcome_checkpoint.json": "f79c30e8d156ed7fbda76e66b5a08b91e3b0ca91de71d9d034ff6d9b2cf7ea0b",
|
".modelhub_state/outcome_checkpoint.json": "70e300a1bea6a1240e5875266f6820d41a8faa635181f63073c648fc46a07d1f",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "1138f6ff3d4a387f335781418eae5f60d8291f48eb315007dba62a41d3ea4742",
|
".modelhub_state/queue_cleanup_latest.json": "1138f6ff3d4a387f335781418eae5f60d8291f48eb315007dba62a41d3ea4742",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "2eadab94ebd717c417889726c443a27066fad416cac7681b31987ec1ac7402ab",
|
".modelhub_state/recent_outcomes.jsonl": "be7198dbec3f0e68487d57d0c60e78c97c0a27f4c0a0287ce995ab5bc58a85a7",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "903e85b5306f570533a8ccbd6191ca1be262ee3b612ae206f56df1c54bda43a3",
|
".modelhub_state/recovery_active_tasks.jsonl": "decfa61332f33234463d154ef6dd4812f1d3a6a2af9653b334b8e99f58d925b1",
|
||||||
".modelhub_state/recovery_intents.jsonl": "adf98384970eba141dfc81e64b2f6a2f2c464271aabc3913e396781e0eb31252",
|
".modelhub_state/recovery_intents.jsonl": "053923de1994f20fd0ba19f949e6faa0f474f907abdcf1c75cddcd11c2cb0f4d",
|
||||||
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
|
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||||
"ledger/submissions.jsonl": "b7a4c9900ee212be7c7f8578a0a71942885eb83e97c5583098a169266bedf55c",
|
"ledger/submissions.jsonl": "b7a4c9900ee212be7c7f8578a0a71942885eb83e97c5583098a169266bedf55c",
|
||||||
"outcomes/submissions.jsonl": "f57697df65065e03324d244151626e83f2a022176b826555fcf66e52609f0644"
|
"outcomes/submissions.jsonl": "f57697df65065e03324d244151626e83f2a022176b826555fcf66e52609f0644"
|
||||||
},
|
},
|
||||||
"generation": 6403,
|
"generation": 6404,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-09-12T22:59:13.225250+00:00",
|
"updatedAt": "2026-09-12T23:02:10.586919+00:00",
|
||||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user