state: generation 6897 (cycle)
This commit is contained in:
@@ -1494,7 +1494,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T21:35:15.928390+00:00",
|
||||
"generatedAt": "2026-09-13T21:38:24.124981+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 75,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 500,
|
||||
"listingErrors": 501,
|
||||
"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": "2026-09-13T21:35:15.897756+00:00",
|
||||
"updatedAt": "2026-09-13T21:38:24.100968+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T21:33:28.127324+00:00",
|
||||
"generatedAt": "2026-09-13T21:36:23.873118+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T21:27:15.319333+00:00",
|
||||
"lastSyncTime": "2026-09-13T21:27:15.041934+00:00",
|
||||
"generatedAt": "2026-09-13T21:36:16.950711+00:00",
|
||||
"lastSyncTime": "2026-09-13T21:36:16.709712+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1981,7 +1981,7 @@
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 110,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"ambiguous_runtime": 22,
|
||||
"framework_architecture_unsupported": 52,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 42,
|
||||
@@ -1989,18 +1989,18 @@
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 166,
|
||||
"failureRate": 0.9171,
|
||||
"failureCount": 167,
|
||||
"failureRate": 0.9176,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0829,
|
||||
"successRate": 0.0824,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 181,
|
||||
"unresolvedFailureCount": 70
|
||||
"total": 182,
|
||||
"unresolvedFailureCount": 71
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
@@ -2509,7 +2509,7 @@
|
||||
"decisionSuccessRate": 0.2584,
|
||||
"decisionTotal": 209,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 143,
|
||||
"ambiguous_runtime": 144,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 99,
|
||||
"memory_capacity": 5,
|
||||
@@ -2519,15 +2519,15 @@
|
||||
"参数/模板问题": 61,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1033,
|
||||
"failureRate": 0.9503,
|
||||
"failureCount": 1034,
|
||||
"failureRate": 0.9504,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 54,
|
||||
"successRate": 0.0497,
|
||||
"total": 1087,
|
||||
"unresolvedFailureCount": 877
|
||||
"successRate": 0.0496,
|
||||
"total": 1088,
|
||||
"unresolvedFailureCount": 878
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 302,
|
||||
@@ -2658,7 +2658,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T21:27:15.315167+00:00",
|
||||
"generatedAt": "2026-09-13T21:36:16.946722+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2827,7 +2827,7 @@
|
||||
"decisionSuccessRate": 0.1327,
|
||||
"decisionTotal": 113,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 21,
|
||||
"ambiguous_runtime": 22,
|
||||
"framework_architecture_unsupported": 54,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 43,
|
||||
@@ -2835,15 +2835,15 @@
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 169,
|
||||
"failureRate": 0.9185,
|
||||
"failureCount": 170,
|
||||
"failureRate": 0.9189,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0815,
|
||||
"total": 184,
|
||||
"unresolvedFailureCount": 70
|
||||
"successRate": 0.0811,
|
||||
"total": 185,
|
||||
"unresolvedFailureCount": 71
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4696,19 +4696,19 @@
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 19,
|
||||
"failureCount": 18,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4720,7 +4720,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 19,
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -4855,22 +4855,22 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 12,
|
||||
"attributableFailureCount": 11,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.7059,
|
||||
"decisionSuccessRate": 0.2941,
|
||||
"decisionTotal": 17,
|
||||
"decisionFailureRate": 0.6875,
|
||||
"decisionSuccessRate": 0.3125,
|
||||
"decisionTotal": 16,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"model_load": 8
|
||||
"model_load": 7
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.75,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-13T16:43:44.912841+00:00",
|
||||
"lastTerminalAt": "2026-09-13T21:36:16.709712+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4879,7 +4879,7 @@
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 3
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7692,15 +7692,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1788,
|
||||
"totalRecords": 1881,
|
||||
"terminalRecords": 1789,
|
||||
"totalRecords": 1882,
|
||||
"totals": {
|
||||
"attributableFailureCount": 530,
|
||||
"decisionFailureRate": 0.8998,
|
||||
"decisionSuccessRate": 0.1002,
|
||||
"decisionTotal": 589,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 417,
|
||||
"ambiguous_runtime": 418,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 335,
|
||||
"memory_capacity": 12,
|
||||
@@ -7712,15 +7712,15 @@
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1729,
|
||||
"failureCount": 1730,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 6,
|
||||
"successCount": 59,
|
||||
"successRate": 0.033,
|
||||
"total": 1788,
|
||||
"unresolvedFailureCount": 1193
|
||||
"total": 1789,
|
||||
"unresolvedFailureCount": 1194
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -7758,6 +7758,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1881,
|
||||
"summarizedRecords": 1882,
|
||||
"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": "2026-09-13T21:36:16.709712+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523305", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 64.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-13T21:27:15.041934+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4581573", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912761+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152538", "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": "2026-09-13T21:09:24.912775+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490277", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834676+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592383", "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": "2026-09-09T18:09:45.834698+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471904", "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": "2026-09-09T18:09:45.834707+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471907", "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": "2026-09-09T17:42:15.798661+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610396", "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
Reference in New Issue
Block a user