state: generation 11231 (cycle)
This commit is contained in:
@@ -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": {
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -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
|
||||
}
|
||||
|
||||
@@ -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
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "c296cd89ece784254a18d9d017cd09429094b58619cf3851843a29017029d074",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "e6aa7b054880fa6495c06964481cdd777d47736f4bf71f5105f47f6440128b72",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "87537b5a91e09c5bbe3cc844d899475d9deb5c4bb1ffc21f9cb83d1e44d259fd",
|
||||
".modelhub_state/official_capabilities.json": "a5bee699d2b2549d72b29b859731cd599958ed40ef1d99d21b22eea1b6657cb0",
|
||||
".modelhub_state/outcome_checkpoint.json": "05bd137019f69f964b03fc04fb475bdaa68d08c68ead8adacb955e30f207ec1b",
|
||||
".modelhub_state/market_intelligence.json": "1eb57f250753e6d9409bd78cdf9294ddfad81c067e5091a3934e5c512cd11293",
|
||||
".modelhub_state/official_capabilities.json": "6a5e7a837039eeb22528ce33c78ae3d77356ca4191d77dd8ed7f50dd8840faa2",
|
||||
".modelhub_state/outcome_checkpoint.json": "e25e7006a2d580c08f54f1a26d546622cbbdddba4c6674c419bff3b9ab8feaba",
|
||||
".modelhub_state/queue_cleanup_latest.json": "0de105598c9478c6cb1c89a58c4794a2395e2c58f508a89a0e4c6fd6e5c312a7",
|
||||
".modelhub_state/recent_outcomes.jsonl": "eed5b73df0d3dd48e504ce46b1a34c1dae52aee702729f4e9173cea1898fc43c",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "8915ac0356f85cfd7501ce2b345bf35c114d669892261722deccc77da0c258ae",
|
||||
".modelhub_state/recovery_intents.jsonl": "ca8c2f96270babe8a6fa6a988d8b0972e70d8163cfadceeb38e453bf6e131e4c",
|
||||
".modelhub_state/recent_outcomes.jsonl": "e5766f5f935cd5d9791e9cd9cff7e0150ae6e454f3cbede5d8bec260006fcfb4",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "774802eee394be9153e9b2fac0f6e24ebb63addc4ff99cc6cdc1b6bce8c61f56",
|
||||
".modelhub_state/recovery_intents.jsonl": "5dc032e0c31c38bf5ad8460d88cb444e7baa550ebbafdf28bfcc2539d11552bc",
|
||||
".modelhub_state/routing_intelligence.json": "ea955c6b3c0bf7864fd2cf8ec51a66c344763482eb7715662096bcaceb384776",
|
||||
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
||||
"ledger/submissions.jsonl": "58a59537cb4094a283f35e457e90c8768740d6be2b2df3b02bdc91c002067f8a",
|
||||
"outcomes/submissions.jsonl": "4d8e82eeb81187a55377572dd6ec2377bc144f64e4348b797834bc7ca65c1c7e"
|
||||
"outcomes/submissions.jsonl": "0a885d88134d5554e9b39378582d68600d45dc9e37828795e5687ebbae2d8066"
|
||||
},
|
||||
"generation": 11230,
|
||||
"generation": 11231,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-21T05:50:49.788070+00:00",
|
||||
"updatedAt": "2026-09-21T05:52:01.642233+00:00",
|
||||
"writerId": "8b35139af6674067a339a670222d4b67"
|
||||
}
|
||||
|
||||
@@ -985,7 +985,7 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443569+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:37:47.189599+00:00", "targetGpu": "Biren_166m", "taskId": "4988061", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443526+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367987, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:37:47.191312+00:00", "targetGpu": "Biren_166m", "taskId": "4988063", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:48:19.353103+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:45:44.135645+00:00", "targetGpu": "Biren_166m", "taskId": "4988230", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T21:47:29.378176+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4988291", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T05:51:50.448422+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:47:29.378176+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4988291", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T21:57:41.600515+00:00", "targetGpu": "Biren_166m", "taskId": "4988391", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T22:11:07.168563+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4988543", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T22:29:12.175799+00:00", "targetGpu": "Biren_166m", "taskId": "4988753", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user