state: generation 11231 (cycle)

This commit is contained in:
2026-09-21 05:52:01 +00:00
parent c754b18172
commit 311151981a
9 changed files with 1757 additions and 1761 deletions

View File

@@ -41,7 +41,7 @@
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 4,
"evidenceCount": 3,
"expiresAt": "2026-10-20T02:52:51.846373+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T02:52:51.846373+00:00",
@@ -51,14 +51,12 @@
"sourceModelIds": [
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
"Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
"ewinregirgojr/Qwen3.8-9B-Instruct-Turbo"
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo"
],
"sourceTaskIds": [
"4969063",
"4969059",
"4969060",
"4969056"
"4969060"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
@@ -2607,7 +2605,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T05:48:19.717172+00:00",
"generatedAt": "2026-09-21T05:51:50.596253+00:00",
"summary": {
"activeBlockCount": 130,
"byGpuFramework": {

View File

@@ -425,7 +425,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T05:50:49.314548+00:00",
"generatedAt": "2026-09-21T05:52:00.632790+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T05:50:49.314548+00:00",
"catalogUpdatedAt": "2026-09-21T05:52:00.632790+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T05:50:49.314548+00:00",
"generatedAt": "2026-09-21T05:52:00.632790+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6500,6 +6500,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T05:50:49.314548+00:00",
"taskTreeUpdatedAt": "2026-09-21T05:52:00.632790+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T05:48:19.649042+00:00",
"lastSyncTime": "2026-09-21T05:48:19.353127+00:00",
"generatedAt": "2026-09-21T05:51:50.525390+00:00",
"lastSyncTime": "2026-09-21T05:51:50.448464+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -45,7 +45,7 @@
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 4,
"evidenceCount": 3,
"expiresAt": "2026-10-20T02:52:51.846373+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T02:52:51.846373+00:00",
@@ -55,14 +55,12 @@
"sourceModelIds": [
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
"Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
"ewinregirgojr/Qwen3.8-9B-Instruct-Turbo"
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo"
],
"sourceTaskIds": [
"4969063",
"4969059",
"4969060",
"4969056"
"4969060"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
@@ -4650,9 +4648,9 @@
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.1262,
"decisionSuccessRate": 0.8738,
"decisionTotal": 103,
"decisionFailureRate": 0.125,
"decisionSuccessRate": 0.875,
"decisionTotal": 104,
"failureBreakdown": {
"ambiguous_runtime": 52,
"context_length": 5,
@@ -4661,16 +4659,16 @@
"验证失败": 32
},
"failureCount": 309,
"failureRate": 0.7744,
"failureRate": 0.7725,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 90,
"successRate": 0.2256,
"successCount": 91,
"successRate": 0.2275,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 399,
"total": 400,
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -5196,9 +5194,9 @@
},
"unknown": {
"attributableFailureCount": 1858,
"decisionFailureRate": 0.6961,
"decisionSuccessRate": 0.3039,
"decisionTotal": 2669,
"decisionFailureRate": 0.6959,
"decisionSuccessRate": 0.3041,
"decisionTotal": 2670,
"failureBreakdown": {
"ambiguous_runtime": 1965,
"architecture_compatibility": 100,
@@ -5216,13 +5214,13 @@
"验证失败": 673
},
"failureCount": 8337,
"failureRate": 0.9113,
"failureRate": 0.9112,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 42,
"successCount": 811,
"successRate": 0.0887,
"total": 9148,
"successCount": 812,
"successRate": 0.0888,
"total": 9149,
"unresolvedFailureCount": 6437
},
"vllm": {
@@ -5393,7 +5391,7 @@
"unresolvedFailureCount": 67
}
},
"generatedAt": "2026-09-21T05:48:19.638018+00:00",
"generatedAt": "2026-09-21T05:51:50.515260+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5720,9 +5718,9 @@
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
"decisionFailureRate": 0.8905,
"decisionSuccessRate": 0.1095,
"decisionTotal": 822,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 823,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -5738,13 +5736,13 @@
"验证失败": 32
},
"failureCount": 1373,
"failureRate": 0.9385,
"failureRate": 0.9378,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 219,
"successCount": 90,
"successRate": 0.0615,
"total": 1463,
"successCount": 91,
"successRate": 0.0622,
"total": 1464,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -15432,21 +15430,21 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T04:51:55.164811+00:00",
"lastTerminalAt": "2026-09-21T05:51:50.448464+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successCount": 6,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -15810,15 +15808,15 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T20:16:30.961280+00:00",
@@ -15831,7 +15829,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 3,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none": {
@@ -32257,13 +32255,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16153,
"totalRecords": 16334,
"terminalRecords": 16154,
"totalRecords": 16335,
"totals": {
"attributableFailureCount": 5854,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6795,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6796,
"failureBreakdown": {
"ambiguous_runtime": 3881,
"architecture_compatibility": 212,
@@ -32286,26 +32284,26 @@
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 923,
"successCount": 941,
"successCount": 942,
"successRate": 0.0583,
"total": 16153,
"total": 16154,
"unresolvedFailureCount": 8435
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-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 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 Cambricon_mlu-370-x4 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-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 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。",
"组合 Iluvatar_bi-150|vllm|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|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。",
@@ -32344,6 +32342,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16334,
"summarizedRecords": 16335,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T05:51:50.448464+00:00", "modelId": "BAAI/Hospitality-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T05:49:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457981", "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": "2026-09-21T05:42:03.443622+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T05:29:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079933", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164989+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:27+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164919+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:26+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4899358", "taskType": "text-generation", "verifyResult": null}
@@ -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": ["qwen3_vl"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:09:29.752180+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.740561+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969062", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T17:09:45.266185+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.693959+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969057", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754925+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.691589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969060", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T16:54:50.062693+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.682339+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969056", "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