state: generation 15684 (cycle)
This commit is contained in:
@@ -3242,7 +3242,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-25T09:24:06.961999+00:00",
|
||||
"generatedAt": "2026-09-25T09:29:39.585657+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 163,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-25T09:28:33.452207+00:00",
|
||||
"generatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-25T09:28:33.452207+00:00",
|
||||
"catalogUpdatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-25T09:28:35.421086+00:00",
|
||||
"generatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6550,6 +6550,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-25T09:28:33.452207+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-25T05:14:51.947130+00:00",
|
||||
"lastSyncTime": "2026-09-25T05:14:51.671721+00:00",
|
||||
"generatedAt": "2026-09-25T09:29:39.500166+00:00",
|
||||
"lastSyncTime": "2026-09-25T09:29:37.557613+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3850,12 +3850,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 21,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 20,
|
||||
"ambiguous_runtime": 21,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 42,
|
||||
"failureCount": 43,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3865,8 +3865,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 42,
|
||||
"unresolvedFailureCount": 21
|
||||
"total": 43,
|
||||
"unresolvedFailureCount": 22
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|feature_emb": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5941,7 +5941,7 @@
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3713,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1560,
|
||||
"ambiguous_runtime": 1561,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 92,
|
||||
@@ -5955,15 +5955,15 @@
|
||||
"tokenizer_compatibility": 415,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6095,
|
||||
"failureCount": 6096,
|
||||
"failureRate": 0.9843,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 869,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0157,
|
||||
"total": 6192,
|
||||
"unresolvedFailureCount": 1610
|
||||
"total": 6193,
|
||||
"unresolvedFailureCount": 1611
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 13,
|
||||
@@ -6113,7 +6113,7 @@
|
||||
"unresolvedFailureCount": 196
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-25T05:14:51.935310+00:00",
|
||||
"generatedAt": "2026-09-25T09:29:39.487405+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6205,7 +6205,7 @@
|
||||
"decisionSuccessRate": 0.0897,
|
||||
"decisionTotal": 814,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 466,
|
||||
"ambiguous_runtime": 467,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 294,
|
||||
@@ -6218,15 +6218,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1564,
|
||||
"failureCount": 1565,
|
||||
"failureRate": 0.9554,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0446,
|
||||
"total": 1637,
|
||||
"unresolvedFailureCount": 807
|
||||
"total": 1638,
|
||||
"unresolvedFailureCount": 808
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -11138,9 +11138,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "gemma2",
|
||||
@@ -11152,8 +11152,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -33517,9 +33517,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -33532,8 +33532,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none|34": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -50462,15 +50462,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17010,
|
||||
"totalRecords": 17230,
|
||||
"terminalRecords": 17011,
|
||||
"totalRecords": 17231,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6103,
|
||||
"decisionFailureRate": 0.8635,
|
||||
"decisionSuccessRate": 0.1365,
|
||||
"decisionTotal": 7068,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4385,
|
||||
"ambiguous_runtime": 4386,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 127,
|
||||
@@ -50486,15 +50486,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16045,
|
||||
"failureCount": 16046,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 935,
|
||||
"successCount": 965,
|
||||
"successRate": 0.0567,
|
||||
"total": 17010,
|
||||
"unresolvedFailureCount": 9007
|
||||
"total": 17011,
|
||||
"unresolvedFailureCount": 9008
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -50552,6 +50552,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17230,
|
||||
"summarizedRecords": 17231,
|
||||
"version": 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": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "20524fe1cbf046ba0f68f5fee9afe7f45b58ec219b92a58452265fb23d7587ab",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "7f40f08e25be12706ba72120fa5a711fed038710d09a7621863527c06b83218f",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "31e254cb01a9d1dcda0b6550837b8763cb955cc21b13872f9a9810071a382651",
|
||||
".modelhub_state/official_capabilities.json": "6ddb50ed807c2a983c299f7e6797c20aa9d55117eb0ff7c3eb753ec4b721a51a",
|
||||
".modelhub_state/outcome_checkpoint.json": "3bc02cce85a07ca085d035b2ca8e8531dcf378948227fdb57246b98ee2fca21a",
|
||||
".modelhub_state/market_intelligence.json": "6c19cb9fe5afdc95e9a9508769f4c43a9a0ac22ed230dbae2094585f5d317ab1",
|
||||
".modelhub_state/official_capabilities.json": "7ffb83714ecc4043f5b52755064b89229db5fa91249ff38f070be01256224479",
|
||||
".modelhub_state/outcome_checkpoint.json": "c9dc2276e83baa2112229547c87f9582fe7d7f7a3fb26c7e71f64e8489162735",
|
||||
".modelhub_state/queue_cleanup_latest.json": "15083a8f261701b8d102a9e49e0322cc70641d25f2a9b54c1e527b8204d6b4c2",
|
||||
".modelhub_state/recent_outcomes.jsonl": "7fe624d0becd5f07cd3e3b24f47d831654564e70deec046b113442b014e07be5",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "c5b48ddea6871f7ba4d1a3f941cb229fd4923fd570f2e66ca6a50b8d9bad4224",
|
||||
".modelhub_state/recovery_intents.jsonl": "2c3b3c43c9a52fac203486657552dc4fcb9e146d544e59e1a78d9b4ef608784c",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "d106c86fbac45f55961fe83ec3bcb917e28bdfc7ad034e0e588ace884f536efa",
|
||||
".modelhub_state/recovery_intents.jsonl": "7a549c81cb80354fb9a82e926737466f84e3c60d85d2692185cd88ca4a5f8cc8",
|
||||
".modelhub_state/routing_intelligence.json": "7d1461fa72783485da7ef3908fb4ca0842188358d92a5b204ebc370354764814",
|
||||
".modelhub_state/submission_exclusions.jsonl": "02c89260955c401737ae26ffb5b4cc542d98dc0cc7e31967a9c71b6b9597ba74",
|
||||
".modelhub_state/worker_crashes.jsonl": "42b4703f3bfb57f9ec8e8f23efdf9b9ccbb11e95f18785217c475c1c2dc44055",
|
||||
"ledger/submissions.jsonl": "3e2deee506be480a6d394637a9e581aa21ca710eec3a450125b6f6fffd7915fa",
|
||||
"outcomes/submissions.jsonl": "0c8b06310fe3e570ea853d06017ec8370539867b989e2ccbfb332a2abc764f64"
|
||||
"outcomes/submissions.jsonl": "13276d1fe31156e373eb87eae1ed63c5e807b3cb7ea6cf068adf65f67f9fe8bb"
|
||||
},
|
||||
"generation": 15683,
|
||||
"generation": 15684,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-25T09:28:35.815124+00:00",
|
||||
"updatedAt": "2026-09-25T09:30:45.557373+00:00",
|
||||
"writerId": "3c776590d60a465490ff1ed12f602b65"
|
||||
}
|
||||
|
||||
@@ -430,7 +430,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556088+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:07.435588+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984361", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556160+00:00", "modelId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720441937, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720441937}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:14.310450+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984367", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:52:39.246386+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:36:14.789170+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984694", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T01:52:39.246416+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020564058}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:44:06.835549+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4984803", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T01:52:39.246349+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:49:20.875289+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984851", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867333+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:59:59.555224+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985000", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:42:24.494006+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T16:44:23.353846+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T18:39:41.567990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985663", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user