state: generation 17715 (cycle)
This commit is contained in:
@@ -3261,7 +3261,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T03:49:01.552052+00:00",
|
||||
"generatedAt": "2026-09-28T03:58:10.258601+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 164,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"generatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"catalogUpdatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"generatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6545,6 +6545,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-28T03:57:04.368437+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-28T03:59:38.569034+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-28T03:31:38.420170+00:00",
|
||||
"lastSyncTime": "2026-09-28T03:31:38.156601+00:00",
|
||||
"generatedAt": "2026-09-28T03:58:10.173772+00:00",
|
||||
"lastSyncTime": "2026-09-28T03:58:09.851955+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3715,27 +3715,27 @@
|
||||
"unresolvedFailureCount": 108
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.7458,
|
||||
"decisionSuccessRate": 0.2542,
|
||||
"decisionTotal": 59,
|
||||
"attributableFailureCount": 45,
|
||||
"decisionFailureRate": 0.75,
|
||||
"decisionSuccessRate": 0.25,
|
||||
"decisionTotal": 60,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 13,
|
||||
"framework_architecture_unsupported": 31,
|
||||
"framework_architecture_unsupported": 32,
|
||||
"model_load": 11,
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 57,
|
||||
"failureRate": 0.7917,
|
||||
"failureCount": 58,
|
||||
"failureRate": 0.7945,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 15,
|
||||
"successRate": 0.2083,
|
||||
"successRate": 0.2055,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 72,
|
||||
"total": 73,
|
||||
"unresolvedFailureCount": 13
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -5957,17 +5957,17 @@
|
||||
"unresolvedFailureCount": 6473
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3623,
|
||||
"attributableFailureCount": 3624,
|
||||
"decisionFailureRate": 0.9739,
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3720,
|
||||
"decisionTotal": 3721,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1584,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1357,
|
||||
"framework_architecture_unsupported": 1358,
|
||||
"memory_capacity": 725,
|
||||
"model_load": 220,
|
||||
"platform_infrastructure": 871,
|
||||
@@ -5976,14 +5976,14 @@
|
||||
"tokenizer_compatibility": 416,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6128,
|
||||
"failureCount": 6129,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 871,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6225,
|
||||
"total": 6226,
|
||||
"unresolvedFailureCount": 1634
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -6134,7 +6134,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T03:31:38.406685+00:00",
|
||||
"generatedAt": "2026-09-28T03:58:10.159678+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6191,15 +6191,15 @@
|
||||
"unresolvedFailureCount": 704
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 187,
|
||||
"decisionFailureRate": 0.8821,
|
||||
"decisionSuccessRate": 0.1179,
|
||||
"decisionTotal": 212,
|
||||
"attributableFailureCount": 188,
|
||||
"decisionFailureRate": 0.8826,
|
||||
"decisionSuccessRate": 0.1174,
|
||||
"decisionTotal": 213,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 251,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 120,
|
||||
"framework_architecture_unsupported": 121,
|
||||
"memory_capacity": 2,
|
||||
"model_load": 23,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -6210,14 +6210,14 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 743,
|
||||
"failureRate": 0.9674,
|
||||
"failureCount": 744,
|
||||
"failureRate": 0.9675,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0326,
|
||||
"total": 768,
|
||||
"successRate": 0.0325,
|
||||
"total": 769,
|
||||
"unresolvedFailureCount": 554
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -10414,6 +10414,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|fp8": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -32822,6 +32845,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|compressed-tensors|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|spark2_5|fp8|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -51479,20 +51526,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17068,
|
||||
"totalRecords": 17289,
|
||||
"terminalRecords": 17069,
|
||||
"totalRecords": 17290,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6116,
|
||||
"attributableFailureCount": 6117,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7082,
|
||||
"decisionTotal": 7083,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4425,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
"context_length": 322,
|
||||
"framework_architecture_unsupported": 2173,
|
||||
"framework_architecture_unsupported": 2174,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 550,
|
||||
"platform_infrastructure": 938,
|
||||
@@ -51503,14 +51550,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16102,
|
||||
"failureCount": 16103,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0566,
|
||||
"total": 17068,
|
||||
"total": 17069,
|
||||
"unresolvedFailureCount": 9048
|
||||
},
|
||||
"warnings": [
|
||||
@@ -51519,15 +51566,15 @@
|
||||
"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。",
|
||||
@@ -51551,6 +51598,7 @@
|
||||
"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。",
|
||||
@@ -51564,11 +51612,10 @@
|
||||
"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": 17289,
|
||||
"summarizedRecords": 17290,
|
||||
"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": "0a45745857954582ac2a67546fcb96afcf914fafeee7a69c35d2a63ba26f802e",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "3039fdae8848d4aecff1094dd5b7c7700624d775f8d6e77e552dc3be2001493f",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "1e7ac5dc1c089ace51ffeebd42264f15a04f6096ded040845dc51154ebe15b95",
|
||||
".modelhub_state/official_capabilities.json": "243add93ed237c6d9d65588321f20e9fdff679fccbcea503c2704d8135c6d43a",
|
||||
".modelhub_state/outcome_checkpoint.json": "4670aca86be46f74ec9cb06456f89dc68aba61ef0b155325cbca3827efc74357",
|
||||
".modelhub_state/market_intelligence.json": "f76e6acc1433556d99797a5711be91e828dcd7e9b297d113eb8decc84ef9ba28",
|
||||
".modelhub_state/official_capabilities.json": "be17be600da23b7b138de483b52940588de666606a9385639cc7a723573fa4ef",
|
||||
".modelhub_state/outcome_checkpoint.json": "e4408ec7aa29356de144c4d4e970c2135984f7f9a7a9966d800fc3fe96eee40a",
|
||||
".modelhub_state/queue_cleanup_latest.json": "7e38abadc6c9b9ae45cfe06be2960ed2213d70309667bb70f63d270b560bc760",
|
||||
".modelhub_state/recent_outcomes.jsonl": "2745ae69199213460dae340cb59923de52e56d054e56d6c25ac1a3b571a88bfc",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "048d2505d3d0fb9e7d015700f2a6a6fe9d030f7e4229eaaf47ef3f938160841b",
|
||||
".modelhub_state/recovery_intents.jsonl": "0e61f96b1aa05ad441f648ca6ffb8e80a3b922380ce1034771756da0a5cc440b",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "5debcb9a20c936fd70115652e0f537512f675fce67ecbdcbc3de27970cfc609f",
|
||||
".modelhub_state/recovery_intents.jsonl": "8f90dd29ff0bb2f7962b3e52fbf993c9a2c1ae3a657e176832ad5eb7ea400bfb",
|
||||
".modelhub_state/routing_intelligence.json": "783dcdd18e65a6df1db492a367c1d1f213fdc7208da4dc91eec95f41c84a2df2",
|
||||
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
|
||||
".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10",
|
||||
"ledger/submissions.jsonl": "c12cccc862c810f341f37c86bed9c9c7e379e2d97976ca4d6698d077c41b91ce",
|
||||
"outcomes/submissions.jsonl": "d61e31bc05e287b849190b644cc42dd0d250b54646df00a76b8700d2cd32b5c4"
|
||||
"outcomes/submissions.jsonl": "77d74c83763ac002979a1735625c7c11c6e1869c05baca835fb0a7b7208e5027"
|
||||
},
|
||||
"generation": 17714,
|
||||
"generation": 17715,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-28T03:57:08.533959+00:00",
|
||||
"updatedAt": "2026-09-28T03:59:46.740155+00:00",
|
||||
"writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea"
|
||||
}
|
||||
|
||||
@@ -134,7 +134,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T20:14:36.914736+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T12:09:15.680573+00:00", "targetGpu": "Vastai_va16", "taskId": "4827491", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-13T22:07:02.846597+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T14:02:33.487789+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T22:28:30.242556+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T14:24:08.911334+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4829350", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-14T03:29:33.013591+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "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": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T19:22:45.622511+00:00", "targetGpu": "Biren_166m", "taskId": "4834315", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T06:17:54.916608+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T22:17:43.666489+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4836986", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525014+00:00", "modelId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "modelProfile": {"architectures": ["Qwen4ExpForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32000153976, "estimatedRequiredGiB": 96.509, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen4_exp", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 14924740499, "modelscopeTags": ["license:other", "model_type:qwen4_exp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen4_exp", "custom_tag:moe", "custom_tag:sparse-attention", "custom_tag:ngram-embedding", "custom_tag:imatrix"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 86355120331}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.810772+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525004+00:00", "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903777808, "estimatedRequiredGiB": 80.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71923892164, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:huihui", "custom_tag:offensive-security", "custom_tag:pentesting", "custom_tag:tool-calling", "custom_tag:cyberstrike", "custom_tag:qwen3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71923892164}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user