state: generation 6811 (cycle)

This commit is contained in:
2026-09-13 16:45:58 +00:00
parent 5cf87af466
commit 20ffce6d08
9 changed files with 2033 additions and 2038 deletions

View File

@@ -270,7 +270,7 @@
"ascend_910-b4|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-12T16:43:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T16:43:21+00:00",
@@ -278,12 +278,10 @@
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8",
"mlx-community/Ornith-1.0-9B-4bit"
"primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
],
"sourceTaskIds": [
"4610337",
"4079339"
"4610337"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
@@ -1475,7 +1473,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T16:42:42.642541+00:00",
"generatedAt": "2026-09-13T16:45:57.769990+00:00",
"summary": {
"activeBlockCount": 74,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"listingErrors": 494,
"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": "2026-09-13T16:42:42.617805+00:00",
"updatedAt": "2026-09-13T16:45:57.745331+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T16:40:29.313847+00:00",
"generatedAt": "2026-09-13T16:43:52.518413+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T16:07:00.346626+00:00",
"lastSyncTime": "2026-09-13T16:07:00.124635+00:00",
"generatedAt": "2026-09-13T16:43:45.226409+00:00",
"lastSyncTime": "2026-09-13T16:43:44.912841+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -274,7 +274,7 @@
"ascend_910-b4|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-12T16:43:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T16:43:21+00:00",
@@ -282,12 +282,10 @@
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8",
"mlx-community/Ornith-1.0-9B-4bit"
"primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
],
"sourceTaskIds": [
"4610337",
"4079339"
"4610337"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
@@ -1957,30 +1955,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 94,
"decisionFailureRate": 0.8624,
"decisionSuccessRate": 0.1376,
"decisionTotal": 109,
"attributableFailureCount": 95,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 110,
"failureBreakdown": {
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 52,
"memory_capacity": 1,
"model_load": 41,
"model_load": 42,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 165,
"failureRate": 0.9167,
"failureCount": 166,
"failureRate": 0.9171,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0833,
"successRate": 0.0829,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 180,
"total": 181,
"unresolvedFailureCount": 70
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2484,29 +2482,29 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 154,
"decisionFailureRate": 0.7404,
"decisionSuccessRate": 0.2596,
"decisionTotal": 208,
"attributableFailureCount": 155,
"decisionFailureRate": 0.7416,
"decisionSuccessRate": 0.2584,
"decisionTotal": 209,
"failureBreakdown": {
"ambiguous_runtime": 143,
"backend_operator": 4,
"framework_architecture_unsupported": 99,
"memory_capacity": 5,
"model_load": 43,
"model_load": 44,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1032,
"failureCount": 1033,
"failureRate": 0.9503,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 54,
"successRate": 0.0497,
"total": 1086,
"total": 1087,
"unresolvedFailureCount": 877
},
"vllm": {
@@ -2638,7 +2636,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T16:07:00.341693+00:00",
"generatedAt": "2026-09-13T16:43:45.221886+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2802,27 +2800,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 96,
"decisionFailureRate": 0.8649,
"decisionSuccessRate": 0.1351,
"decisionTotal": 111,
"attributableFailureCount": 97,
"decisionFailureRate": 0.8661,
"decisionSuccessRate": 0.1339,
"decisionTotal": 112,
"failureBreakdown": {
"ambiguous_runtime": 21,
"framework_architecture_unsupported": 53,
"memory_capacity": 1,
"model_load": 42,
"model_load": 43,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 167,
"failureRate": 0.9176,
"failureCount": 168,
"failureRate": 0.918,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 15,
"successRate": 0.0824,
"total": 182,
"successRate": 0.082,
"total": 183,
"unresolvedFailureCount": 70
},
"Kunlunxin_p-800": {
@@ -4742,7 +4740,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 2,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.7059,
"decisionSuccessRate": 0.2941,
@@ -4756,7 +4754,7 @@
"failureRate": 0.75,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T16:07:00.124635+00:00",
"lastTerminalAt": "2026-09-13T16:43:44.912841+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7457,19 +7455,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1776,
"totalRecords": 1863,
"terminalRecords": 1777,
"totalRecords": 1864,
"totals": {
"attributableFailureCount": 520,
"decisionFailureRate": 0.8981,
"decisionSuccessRate": 0.1019,
"decisionTotal": 579,
"attributableFailureCount": 521,
"decisionFailureRate": 0.8983,
"decisionSuccessRate": 0.1017,
"decisionTotal": 580,
"failureBreakdown": {
"ambiguous_runtime": 417,
"backend_operator": 43,
"framework_architecture_unsupported": 329,
"memory_capacity": 11,
"model_load": 73,
"model_load": 74,
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
@@ -7477,14 +7475,14 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1717,
"failureCount": 1718,
"failureRate": 0.9668,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0332,
"total": 1776,
"total": 1777,
"unresolvedFailureCount": 1193
},
"warnings": [
@@ -7522,6 +7520,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1863,
"summarizedRecords": 1864,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-13T16:43:44.912841+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T16:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523221", "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": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-13T16:07:00.124635+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T16:01:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4595685", "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": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-13T15:06:31.804323+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T14:59:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493602", "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": "2026-09-13T13:43:30.144198+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T13:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332459", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T16:50:57.940039+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T16:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610347", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-09T16:11:26.734386+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T16:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477958", "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": "2026-09-09T16:03:52.328406+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T15:55:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493674", "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": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-09T15:39:07.233616+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T15:33:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079339", "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