state: generation 10938 (cycle)

This commit is contained in:
2026-09-20 22:17:09 +00:00
parent 6fec0d97e0
commit 525c78a726
9 changed files with 1831 additions and 1834 deletions

View File

@@ -1005,7 +1005,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 4,
"evidenceCount": 3,
"expiresAt": "2026-10-20T18:51:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T18:51:21+00:00",
@@ -1015,14 +1015,12 @@
"sourceModelIds": [
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
"EschaLabs/Qwen3.8-27B-Escha-W2"
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU"
],
"sourceTaskIds": [
"4523697",
"4490374",
"4460362",
"4595432"
"4460362"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -2285,7 +2283,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-20T21:55:29.314192+00:00",
"generatedAt": "2026-09-20T22:16:58.799484+00:00",
"summary": {
"activeBlockCount": 112,
"byGpuFramework": {

View File

@@ -425,7 +425,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T22:15:57.582209+00:00",
"generatedAt": "2026-09-20T22:17:07.666131+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-20T22:15:57.582209+00:00",
"catalogUpdatedAt": "2026-09-20T22:17:07.666131+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-20T22:15:57.582209+00:00",
"generatedAt": "2026-09-20T22:17:07.666131+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6455,6 +6455,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-20T22:15:57.582209+00:00",
"taskTreeUpdatedAt": "2026-09-20T22:17:07.666131+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T21:55:44.447564+00:00",
"lastSyncTime": "2026-09-20T21:55:44.371069+00:00",
"generatedAt": "2026-09-20T22:16:58.735090+00:00",
"lastSyncTime": "2026-09-20T22:16:58.665942+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1009,7 +1009,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 4,
"evidenceCount": 3,
"expiresAt": "2026-10-20T18:51:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T18:51:21+00:00",
@@ -1019,14 +1019,12 @@
"sourceModelIds": [
"logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
"EschaLabs/Qwen3.8-27B-Escha-W2"
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU"
],
"sourceTaskIds": [
"4523697",
"4490374",
"4460362",
"4595432"
"4460362"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -3861,9 +3859,9 @@
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 87,
"参数/模板问题": 2
"参数/模板问题": 3
},
"failureCount": 89,
"failureCount": 90,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3873,8 +3871,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 89,
"unresolvedFailureCount": 89
"total": 90,
"unresolvedFailureCount": 90
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
@@ -5002,17 +5000,17 @@
"model_load": 1,
"platform_infrastructure": 16,
"tokenizer_compatibility": 82,
"参数/模板问题": 8
"参数/模板问题": 9
},
"failureCount": 271,
"failureCount": 272,
"failureRate": 0.9891,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 3,
"successRate": 0.0109,
"total": 274,
"unresolvedFailureCount": 137
"total": 275,
"unresolvedFailureCount": 138
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 44,
@@ -5036,7 +5034,7 @@
"unresolvedFailureCount": 37
}
},
"generatedAt": "2026-09-20T21:55:44.436706+00:00",
"generatedAt": "2026-09-20T22:16:58.725557+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 81,
@@ -5268,19 +5266,19 @@
"ambiguous_runtime": 161,
"framework_architecture_unsupported": 8,
"memory_capacity": 1,
"参数/模板问题": 2,
"参数/模板问题": 3,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 196,
"failureCount": 197,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 196,
"unresolvedFailureCount": 187
"total": 197,
"unresolvedFailureCount": 188
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -13401,9 +13399,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 5,
"参数/模板问题": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -13415,8 +13414,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
@@ -13783,18 +13782,18 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|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": 5,
"framework_architecture_unsupported": 8,
"framework_architecture_unsupported": 7,
"runtime_memory": 1
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -13806,7 +13805,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 14,
"total": 13,
"unresolvedFailureCount": 5
}
},
@@ -27574,8 +27573,8 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 15975,
"totalRecords": 16131,
"terminalRecords": 15976,
"totalRecords": 16132,
"totals": {
"attributableFailureCount": 5806,
"decisionFailureRate": 0.8617,
@@ -27594,19 +27593,19 @@
"repository_structure": 734,
"runtime_memory": 82,
"tokenizer_compatibility": 658,
"参数/模板问题": 3111,
"参数/模板问题": 3112,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15043,
"failureCount": 15044,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 932,
"successRate": 0.0583,
"total": 15975,
"unresolvedFailureCount": 8315
"total": 15976,
"unresolvedFailureCount": 8316
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -27653,12 +27652,12 @@
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 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 Iluvatar_bi-150|transformers|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 Cambricon_mlu-370-x8|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 Ascend_910-b3|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-b3|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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16131,
"summarizedRecords": 16132,
"version": 1
}

View File

@@ -182,6 +182,7 @@
{"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", "failureUnsupportedArchitectures": ["SophiaForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T06:27:54.872414+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T17:18:17.894388+00:00", "targetGpu": "Biren_166m", "taskId": "4960871", "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": "2026-09-20T07:46:21.355476+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T17:00:42.497473+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4960599", "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": "2026-09-20T19:49:26.756443+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T16:40:56.572866+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4960315", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T22:16:58.665942+00:00", "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-19T16:40:56.513852+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4960317", "taskType": "text-generation", "verifyResult": null}
{"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_tokenizer_patch", "lastSyncTime": "2026-09-20T01:06:12.681494+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 4281947881, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T12:27:16.554034+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4956471", "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": "2026-09-20T03:35:24.469804+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 4281945939, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T12:09:02.671570+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4956162", "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": "2026-09-19T02:10:43.202143+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T02:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609094", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T10:23:01.246264+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T10:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590619", "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": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938151+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4594446", "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", "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938183+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590565", "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": "2026-09-15T09:23:51.409303+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595432", "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