state: generation 17354 (cycle)
This commit is contained in:
@@ -3261,7 +3261,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-27T13:43:23.104832+00:00",
|
||||
"generatedAt": "2026-09-27T13:48:29.907288+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 164,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-27T13:47:27.348162+00:00",
|
||||
"generatedAt": "2026-09-27T13:49:17.956889+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-27T13:47:27.348162+00:00",
|
||||
"catalogUpdatedAt": "2026-09-27T13:49:17.956889+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-27T13:47:27.348162+00:00",
|
||||
"generatedAt": "2026-09-27T13:49:17.956889+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6197,6 +6197,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-27T13:47:27.348162+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-27T13:49:17.956889+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-27T13:43:23.022567+00:00",
|
||||
"lastSyncTime": "2026-09-27T13:43:22.766786+00:00",
|
||||
"generatedAt": "2026-09-27T13:48:29.825492+00:00",
|
||||
"lastSyncTime": "2026-09-27T13:48:29.557196+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3871,12 +3871,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 41,
|
||||
"ambiguous_runtime": 42,
|
||||
"framework_architecture_unsupported": 23,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 66,
|
||||
"failureCount": 67,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3886,8 +3886,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 66,
|
||||
"unresolvedFailureCount": 42
|
||||
"total": 67,
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|feature_emb": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5962,7 +5962,7 @@
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3720,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1581,
|
||||
"ambiguous_runtime": 1582,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
@@ -5976,15 +5976,15 @@
|
||||
"tokenizer_compatibility": 416,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6125,
|
||||
"failureCount": 6126,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 871,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6222,
|
||||
"unresolvedFailureCount": 1631
|
||||
"total": 6223,
|
||||
"unresolvedFailureCount": 1632
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 13,
|
||||
@@ -6134,7 +6134,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-27T13:43:23.009548+00:00",
|
||||
"generatedAt": "2026-09-27T13:48:29.813327+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6226,7 +6226,7 @@
|
||||
"decisionSuccessRate": 0.0894,
|
||||
"decisionTotal": 817,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 500,
|
||||
"ambiguous_runtime": 501,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 297,
|
||||
@@ -6239,15 +6239,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1602,
|
||||
"failureCount": 1603,
|
||||
"failureRate": 0.9564,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0436,
|
||||
"total": 1675,
|
||||
"unresolvedFailureCount": 842
|
||||
"total": 1676,
|
||||
"unresolvedFailureCount": 843
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -11412,9 +11412,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8
|
||||
"ambiguous_runtime": 9
|
||||
},
|
||||
"failureCount": 8,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
@@ -11426,8 +11426,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 8
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -34336,6 +34336,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -51361,15 +51385,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17062,
|
||||
"totalRecords": 17283,
|
||||
"terminalRecords": 17063,
|
||||
"totalRecords": 17284,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6114,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7080,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4421,
|
||||
"ambiguous_runtime": 4422,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -51385,15 +51409,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16096,
|
||||
"failureCount": 16097,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0566,
|
||||
"total": 17062,
|
||||
"unresolvedFailureCount": 9044
|
||||
"total": 17063,
|
||||
"unresolvedFailureCount": 9045
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -51401,15 +51425,15 @@
|
||||
"GPU Ascend_910-b4 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 MetaX_c-500 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 Vastai_va16 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 Ascend_910-b3 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 Biren_166m 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 Iluvatar_bi-100 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 Mthreads_s4000 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。",
|
||||
"组合 Ascend_910-b3|vllm_tokenizer_patch|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-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -51433,6 +51457,7 @@
|
||||
"组合 Cambricon_mlu-370-x4|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 hygon_k100-ai|vllm-patch-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 Vastai_va16|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 Iluvatar_mrv-100|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 Mthreads_s4000|llamacpp|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-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -51446,11 +51471,10 @@
|
||||
"组合 Cambricon_mlu-370-x4|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 Mthreads_s4000|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 Kunlunxin_p-800|vllm_tokenizer_patch|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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Vastai_va16|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 Iluvatar_bi-150|llamacpp|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": 17283,
|
||||
"summarizedRecords": 17284,
|
||||
"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": "5070c8855801b32c54ef3fafec23d97ea8c1966d23c7a4b06cebe07ff1ffc681",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "47c1df588501dba4b38e9f7f9cda7d47a14a9a7a2a358f10f53e934797e39490",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "782974b7b7ea26a995f2758db9eebcd52b140221fd22c7116036a6fef03f3199",
|
||||
".modelhub_state/official_capabilities.json": "add33f016f54ca3d04017d994818faf7145c07bb6344b30c6a277f2612570e94",
|
||||
".modelhub_state/outcome_checkpoint.json": "803cbb141df92f7314ddc5a4c242c011e013c5dca6c55b8e98ca670e41be4a9c",
|
||||
".modelhub_state/market_intelligence.json": "a172b5f7aca7acbc521077c281ea88d5bc41e30af34d6824f421e3eee14b1708",
|
||||
".modelhub_state/official_capabilities.json": "4b0fd95a739848d76ff742919bbe710456d2cf7648cc3929f1aec8e453b96e25",
|
||||
".modelhub_state/outcome_checkpoint.json": "704adf4a0379763468a8a7ae588bdd62247269b6d02a1df9371abfc3faf5b849",
|
||||
".modelhub_state/queue_cleanup_latest.json": "694bb6e81572a5a5f3e554e2c6eff62ff80ba911ec7f055a8070daa352e6f6d3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "29de8caa53d34c5cd69118aa9b7b19270cfeb5f2ed4f79592568a96e8c2790ab",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "929b78323ee68b36340c34af9896c675b70336e1b71725342881745b0547ebf5",
|
||||
".modelhub_state/recovery_intents.jsonl": "755028038eb4aeef0d6fa669537d89843274ed46677c55e5762bf99b222bebc8",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "86f16891f4ce0a7ae66d60b803df983ad65db4edffeb4b419b1a6986d1a07f6a",
|
||||
".modelhub_state/recovery_intents.jsonl": "92fa5e6160a9a8f56b8c6f5fefdc8a3ab7577527aab62bd7c04e445279ba736a",
|
||||
".modelhub_state/routing_intelligence.json": "940f3a27b4aa80bccab68a19868dfe16bdc2da61adca80cc729072db1147d4bf",
|
||||
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
|
||||
".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10",
|
||||
"ledger/submissions.jsonl": "d755fba92856e017c43d5eb270847de33b9fb6258ecf81f004f5dcee116b1aca",
|
||||
"outcomes/submissions.jsonl": "9c5719794aeb2cd813057022ddd36fe0d9dfb7b66277711e4f9b3d7d68dbb32c"
|
||||
"outcomes/submissions.jsonl": "fb0c17c5c9574795191f3ea36c76f07e5199e2f71be8cee378390b07f96e152d"
|
||||
},
|
||||
"generation": 17353,
|
||||
"generation": 17354,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-27T13:47:28.218242+00:00",
|
||||
"updatedAt": "2026-09-27T13:49:21.422700+00:00",
|
||||
"writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea"
|
||||
}
|
||||
|
||||
@@ -424,7 +424,6 @@
|
||||
{"failReason": null, "framework": "transformers", "lastSyncTime": "2026-09-21T04:11:57.967204+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "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": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:09:23.973756+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986856", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "transformers", "lastSyncTime": "2026-09-21T04:11:57.967149+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:09:24.163788+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986867", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "transformers", "lastSyncTime": "2026-09-21T04:11:57.967122+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:09:24.460163+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986875", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T05:25:05.959941+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "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", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:22:47.667525+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4987928", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T05:42:03.443555+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:26:40.552644+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4987963", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443590+00:00", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:28:22.564707+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4988004", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T06:13:12.662977+00:00", "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": "waiting", "submitTime": "2026-09-20T22:11:07.168563+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4988543", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user