state: generation 4940 (cycle)
This commit is contained in:
@@ -1306,7 +1306,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T03:59:09.192440+00:00",
|
||||
"generatedAt": "2026-09-10T04:01:54.724985+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 65,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 351,
|
||||
"listingErrors": 352,
|
||||
"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": "2026-09-10T03:59:09.167128+00:00",
|
||||
"updatedAt": "2026-09-10T04:01:54.694031+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T03:57:31.899272+00:00",
|
||||
"generatedAt": "2026-09-10T04:00:16.124696+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T03:15:36.085648+00:00",
|
||||
"lastSyncTime": "2026-09-10T03:15:35.806659+00:00",
|
||||
"generatedAt": "2026-09-10T04:00:10.615681+00:00",
|
||||
"lastSyncTime": "2026-09-10T04:00:09.998782+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1738,26 +1738,26 @@
|
||||
"unresolvedFailureCount": 31
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 4,
|
||||
"attributableFailureCount": 4,
|
||||
"decisionFailureRate": 0.8,
|
||||
"decisionSuccessRate": 0.2,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureRate": 0.8333,
|
||||
"failureCount": 6,
|
||||
"failureRate": 0.8571,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.1667,
|
||||
"successRate": 0.1429,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
@@ -1990,20 +1990,20 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 28,
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 28,
|
||||
"decisionTotal": 29,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"backend_operator": 1,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 51,
|
||||
"failureCount": 52,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2013,7 +2013,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 51,
|
||||
"total": 52,
|
||||
"unresolvedFailureCount": 23
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
@@ -2309,13 +2309,13 @@
|
||||
"unresolvedFailureCount": 830
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 227,
|
||||
"attributableFailureCount": 228,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 227,
|
||||
"decisionTotal": 228,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 131,
|
||||
"backend_operator": 22,
|
||||
"backend_operator": 23,
|
||||
"framework_architecture_unsupported": 168,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 18,
|
||||
@@ -2325,14 +2325,14 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 380,
|
||||
"failureCount": 381,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 380,
|
||||
"total": 381,
|
||||
"unresolvedFailureCount": 152
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2375,23 +2375,23 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"vllm_0_17_0_corex_4_4_0": {
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 4,
|
||||
"attributableFailureCount": 4,
|
||||
"decisionFailureRate": 0.8,
|
||||
"decisionSuccessRate": 0.2,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureRate": 0.8333,
|
||||
"failureCount": 6,
|
||||
"failureRate": 0.8571,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.1667,
|
||||
"total": 6,
|
||||
"successRate": 0.1429,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
@@ -2436,7 +2436,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T03:15:36.079303+00:00",
|
||||
"generatedAt": "2026-09-10T04:00:10.611135+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2575,27 +2575,27 @@
|
||||
"unresolvedFailureCount": 26
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"attributableFailureCount": 18,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 24,
|
||||
"attributableFailureCount": 19,
|
||||
"decisionFailureRate": 0.76,
|
||||
"decisionSuccessRate": 0.24,
|
||||
"decisionTotal": 25,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 4,
|
||||
"backend_operator": 5,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 4,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 59,
|
||||
"failureRate": 0.9077,
|
||||
"failureCount": 60,
|
||||
"failureRate": 0.9091,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 6,
|
||||
"successRate": 0.0923,
|
||||
"total": 65,
|
||||
"successRate": 0.0909,
|
||||
"total": 66,
|
||||
"unresolvedFailureCount": 41
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
@@ -2667,13 +2667,13 @@
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.9355,
|
||||
"decisionSuccessRate": 0.0645,
|
||||
"decisionTotal": 31,
|
||||
"attributableFailureCount": 30,
|
||||
"decisionFailureRate": 0.9375,
|
||||
"decisionSuccessRate": 0.0625,
|
||||
"decisionTotal": 32,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"backend_operator": 1,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
@@ -2682,14 +2682,14 @@
|
||||
"参数/模板问题": 7,
|
||||
"验证失败": 26
|
||||
},
|
||||
"failureCount": 85,
|
||||
"failureRate": 0.977,
|
||||
"failureCount": 86,
|
||||
"failureRate": 0.9773,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.023,
|
||||
"total": 87,
|
||||
"successRate": 0.0227,
|
||||
"total": 88,
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
@@ -3148,15 +3148,15 @@
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 0.6667,
|
||||
"decisionSuccessRate": 0.3333,
|
||||
"decisionTotal": 3,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2
|
||||
"backend_operator": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureRate": 0.6667,
|
||||
"failureCount": 3,
|
||||
"failureRate": 0.75,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
@@ -3164,10 +3164,10 @@
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 1,
|
||||
"successRate": 0.3333,
|
||||
"successRate": 0.25,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none": {
|
||||
@@ -4396,23 +4396,24 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"backend_operator": 1,
|
||||
"model_load": 2,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-09T21:11:06.904677+00:00",
|
||||
"lastTerminalAt": "2026-09-10T04:00:09.998782+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4420,7 +4421,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
@@ -4633,12 +4634,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 1,
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4650,8 +4651,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 6
|
||||
}
|
||||
},
|
||||
"recentProfileCombinationStats": {
|
||||
@@ -5732,14 +5733,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
"backend_operator": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -5752,7 +5753,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|31": {
|
||||
@@ -6812,16 +6813,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1492,
|
||||
"totalRecords": 1576,
|
||||
"terminalRecords": 1494,
|
||||
"totalRecords": 1578,
|
||||
"totals": {
|
||||
"attributableFailureCount": 395,
|
||||
"decisionFailureRate": 0.8896,
|
||||
"decisionSuccessRate": 0.1104,
|
||||
"decisionTotal": 444,
|
||||
"attributableFailureCount": 397,
|
||||
"decisionFailureRate": 0.8901,
|
||||
"decisionSuccessRate": 0.1099,
|
||||
"decisionTotal": 446,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 279,
|
||||
"backend_operator": 26,
|
||||
"backend_operator": 28,
|
||||
"framework_architecture_unsupported": 269,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 46,
|
||||
@@ -6832,21 +6833,21 @@
|
||||
"参数/模板问题": 94,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1443,
|
||||
"failureCount": 1445,
|
||||
"failureRate": 0.9672,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 49,
|
||||
"successRate": 0.0328,
|
||||
"total": 1492,
|
||||
"total": 1494,
|
||||
"unresolvedFailureCount": 1046
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -6854,7 +6855,7 @@
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU 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 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -6875,6 +6876,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1576,
|
||||
"summarizedRecords": 1578,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T04:00:09.998782+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T03:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532022", "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": "2026-09-10T02:50:12.317776+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493607", "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": "2026-09-10T02:50:12.317748+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4271675", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "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": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T08:32:22.399378+00:00", "modelId": "microsoft/Dayhoff-3b-GR-HM-c", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T08:31:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079222", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-07T08:32:22.399402+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T08:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083445", "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": "2026-09-07T08:04:59.604222+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464045", "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": "2026-09-07T07:41:41.205199+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:33:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459518", "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": "e128a7f907edb21689e69388677594e99d30d7b40461fd3aa5fc73e11d86ae80",
|
||||
".modelhub_state/architecture_history_backfill.json": "d64ed2095bec337a1cdcd21492ec9700c73e7217ac9cd5e2b354292b467ddbb6",
|
||||
".modelhub_state/market_intelligence.json": "3407ce6b1039c5350ea1bddc0e87baa3041943a402bbae4af7b6d591991b9c54",
|
||||
".modelhub_state/official_capabilities.json": "26ee91eeaf8b80bc25489d160ce5558006476e6255908e30ffae53eefb712e2d",
|
||||
".modelhub_state/outcome_checkpoint.json": "b90423098699ba6c0a7dbb753774a427230c8930321f117c34b2bbd67be30796",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "ba2e6dc38cc67174d0f11193713ea0075249adcd60279acfb4b87039c83edbc0",
|
||||
".modelhub_state/architecture_history_backfill.json": "a8dfaaa36d1fbaf69b9bd4726ab23a01e3bb5c2b230a4622f5fa7f4981f5d842",
|
||||
".modelhub_state/market_intelligence.json": "f151781292b92fa735c7ff2c5fa05b0765dff833e5693bf17c0455e762546471",
|
||||
".modelhub_state/official_capabilities.json": "bb7cc5d25e4ee8da891797befd5a31f70eb5c46309677c77f7e0dd7d54a6d6d8",
|
||||
".modelhub_state/outcome_checkpoint.json": "21b8f93edfb01155f3d4292f09c54b09803a87771ab05601eb50e4200d648ab9",
|
||||
".modelhub_state/queue_cleanup_latest.json": "1ff9cf1dcc1b2c2557b532394e1e76da55fa710317d6832581664c56c6ecc7b3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "da87468be4ce603c73643d396ababb0efbfdc2c7827ed09fbedd200012c6de95",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "b241fc921a93119c2c41dc53a66069f4d384ab3d3eb88065af369ba060ee5959",
|
||||
".modelhub_state/recovery_intents.jsonl": "071e62200171f3d09b9a109eb29295b4663dbd1982973d4d1d56bb75669f8966",
|
||||
".modelhub_state/recent_outcomes.jsonl": "b67553bcb9f2ada574769d6c2bb29fb2d3cf825d842a90227c9617b6fc326f46",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "ac5819621373195dfda37f2c2f3312891cdc13865807228caaafea5ca256595d",
|
||||
".modelhub_state/recovery_intents.jsonl": "4362b8a9b39faaba39db64550439747ab645e3d1681ad76993429dac97711d6d",
|
||||
".modelhub_state/routing_intelligence.json": "2c10dfed0a26c6bc51f09f69009667713989adad52ee2398495736003f8b05c0",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "b6eb40c31ab1c1a191127833e3d1de4af7d89da6b771f6b6b49f4125567e36fb",
|
||||
"outcomes/submissions.jsonl": "cf22e03f4ce248db00a4d8578edc3fa6a80aca60ad18f3f6b31eedc17c4b920f"
|
||||
"outcomes/submissions.jsonl": "16e655505b055cca9b9c7137e60aa248f51338d1b01f94ad6a9dbda7c6832215"
|
||||
},
|
||||
"generation": 4939,
|
||||
"generation": 4940,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T03:59:09.286991+00:00",
|
||||
"updatedAt": "2026-09-10T04:01:55.658125+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
@@ -100,7 +100,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T10:41:43.740753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5709884743}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T02:38:10.748196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4639409", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T12:57:50.112671+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081293776, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504091, "modelscopeLicense": "llama3", "modelscopeParams": 8030261312, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.822669+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641482", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T12:57:50.112639+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:26.818323+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641464", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397755+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397684+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.008584+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641565", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user