state: generation 5275 (cycle)
This commit is contained in:
@@ -1311,7 +1311,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T17:02:44.798981+00:00",
|
||||
"generatedAt": "2026-09-10T17:06:07.617336+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -35,7 +35,7 @@
|
||||
"2": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 375,
|
||||
"listingErrors": 376,
|
||||
"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": 2,
|
||||
"nextAccountIndex": 3,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T17:02:44.771774+00:00",
|
||||
"updatedAt": "2026-09-10T17:06:07.591759+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T17:01:10.633350+00:00",
|
||||
"generatedAt": "2026-09-10T17:03:52.749669+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T16:54:17.522980+00:00",
|
||||
"lastSyncTime": "2026-09-10T16:54:17.206935+00:00",
|
||||
"generatedAt": "2026-09-10T17:03:45.849687+00:00",
|
||||
"lastSyncTime": "2026-09-10T17:03:45.496018+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1545,24 +1545,24 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 24,
|
||||
"ambiguous_runtime": 27,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 83,
|
||||
"failureRate": 0.9765,
|
||||
"failureCount": 86,
|
||||
"failureRate": 0.9773,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0235,
|
||||
"successRate": 0.0227,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 85,
|
||||
"unresolvedFailureCount": 63
|
||||
"total": 88,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2296,7 +2296,7 @@
|
||||
"decisionSuccessRate": 0.2759,
|
||||
"decisionTotal": 174,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 118,
|
||||
"ambiguous_runtime": 121,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"memory_capacity": 5,
|
||||
@@ -2305,15 +2305,15 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 973,
|
||||
"failureRate": 0.953,
|
||||
"failureCount": 976,
|
||||
"failureRate": 0.9531,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.047,
|
||||
"total": 1021,
|
||||
"unresolvedFailureCount": 847
|
||||
"successRate": 0.0469,
|
||||
"total": 1024,
|
||||
"unresolvedFailureCount": 850
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 240,
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T16:54:17.517562+00:00",
|
||||
"generatedAt": "2026-09-10T17:03:45.844966+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2523,21 +2523,21 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 24,
|
||||
"ambiguous_runtime": 27,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 83,
|
||||
"failureRate": 0.9765,
|
||||
"failureCount": 86,
|
||||
"failureRate": 0.9773,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0235,
|
||||
"total": 85,
|
||||
"unresolvedFailureCount": 63
|
||||
"successRate": 0.0227,
|
||||
"total": 88,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -4116,15 +4116,15 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"ambiguous_runtime": 14,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 13,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T16:54:17.206907+00:00",
|
||||
"lastTerminalAt": "2026-09-10T17:03:45.496007+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4132,8 +4132,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 11
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4343,42 +4343,19 @@
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 18
|
||||
},
|
||||
"MetaX_c-500|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-08T06:21:18.620967+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 8,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"model_load": 2
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4390,7 +4367,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -7193,15 +7170,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1610,
|
||||
"totalRecords": 1697,
|
||||
"terminalRecords": 1613,
|
||||
"totalRecords": 1700,
|
||||
"totals": {
|
||||
"attributableFailureCount": 421,
|
||||
"decisionFailureRate": 0.8901,
|
||||
"decisionSuccessRate": 0.1099,
|
||||
"decisionTotal": 473,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 363,
|
||||
"ambiguous_runtime": 366,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"memory_capacity": 11,
|
||||
@@ -7213,31 +7190,30 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1558,
|
||||
"failureRate": 0.9677,
|
||||
"failureCount": 1561,
|
||||
"failureRate": 0.9678,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 52,
|
||||
"successRate": 0.0323,
|
||||
"total": 1610,
|
||||
"unresolvedFailureCount": 1134
|
||||
"successRate": 0.0322,
|
||||
"total": 1613,
|
||||
"unresolvedFailureCount": 1137
|
||||
},
|
||||
"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。",
|
||||
@@ -7252,10 +7228,11 @@
|
||||
"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": 1697,
|
||||
"summarizedRecords": 1700,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,6 @@
|
||||
{"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": "2026-09-10T17:03:45.496007+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497067", "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": "2026-09-10T17:03:45.496018+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496941", "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": "2026-09-10T17:03:45.495985+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497055", "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": "2026-09-10T16:54:17.206907+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497075", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T16:54:17.206935+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:45:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532021", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T16:37:38.117587+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505124", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -295,6 +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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T15:41:33.599000+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2023929984, "estimatedRequiredGiB": 2.272, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033083373, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033083377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.795745+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712800", "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-mlu", "lastSyncTime": "2026-09-10T07:53:10.699404+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9517467172, "estimatedRequiredGiB": 10.647, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9526650722, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9526650722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.780642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712802", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T06:39:56.007893+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079272", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-08T06:21:18.620967+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-08T06:11:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4525689", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T06:03:35.611314+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:03:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079395", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T05:49:30.800091+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T05:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079985", "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": "74b822c67298d15a6cb78c05d8cf6bb1e30566d4702942804aa5e804f70a0f6b",
|
||||
".modelhub_state/architecture_history_backfill.json": "58bbde0c584887bfbffb3af549ca7cb7f2e4a77851aaccd4f21fc85119be2802",
|
||||
".modelhub_state/market_intelligence.json": "7ec226b4a4733ffabc5e767a8d2de5a20a56a95c56388564c846a9210b80cc6d",
|
||||
".modelhub_state/official_capabilities.json": "656d2c00d734e88d28e7532daddabcae5e78be0a84c5458321aea9e98767663f",
|
||||
".modelhub_state/outcome_checkpoint.json": "f8915f4d8eefb5368690eef515748467d4fc4660d5c8f851e1dd84747bd9817c",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "f3d70adf854f83ab8646dbe90ee3baf7fa7fb9f73400cceedefaf3a73ddba34d",
|
||||
".modelhub_state/architecture_history_backfill.json": "f62a0df21e1ec2281020e0ec80da8378573d223309b2b9c6213e50ab0cdddee9",
|
||||
".modelhub_state/market_intelligence.json": "6b71a9eb6eabbcfd715c93c65323a29bf8de8227433b1fc0aca151075640fca3",
|
||||
".modelhub_state/official_capabilities.json": "9c3e46e171f5666ef546bb3599d0688842a34bdb3dde2f9a7f740b544fba641c",
|
||||
".modelhub_state/outcome_checkpoint.json": "58dca2c650e2e435bdadef4bb8aa6210e1223faf7792a27aea926c54c75a6c2f",
|
||||
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
|
||||
".modelhub_state/recent_outcomes.jsonl": "83bde283f815736ab38036c5b31fbb67a03aee802e47a1babd2bbf9ca58a261f",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "7c89929110d728449e26e82d186f01564da4b59ae6d2a1814d643e583ab365a6",
|
||||
".modelhub_state/recovery_intents.jsonl": "cf12e30a38ffd029aa993ad4300c6f1a1320c0dc8a1955523f39806012d9b03e",
|
||||
".modelhub_state/recent_outcomes.jsonl": "7f4ac32e039b9a5ee5874d379d84c1c45ff6e21f6f7602ac690e13e5da798838",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "f059f956335414f642cf567a5e91fe7ab675fe88f781c57d96a8028de8ecbaff",
|
||||
".modelhub_state/recovery_intents.jsonl": "8a7a71a7fc2b4b3a7f0f0df4e19aa4f6a1b06018f13638185b4f0da8d2bc7fa5",
|
||||
".modelhub_state/routing_intelligence.json": "bcaf2013af1725c91c403ee60ebea6ce240abe9c172497b6086649b19fe2a2a9",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "b825b21af42e5406538478522c80028c136d59b0b4682500784c593298293d8b",
|
||||
"outcomes/submissions.jsonl": "a586cdf2049d2a9903a1e7b423d740a29c6547aac344621237f61dc993f79af7"
|
||||
},
|
||||
"generation": 5274,
|
||||
"generation": 5275,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T17:02:44.898277+00:00",
|
||||
"updatedAt": "2026-09-10T17:06:08.155220+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user