state: generation 18119 (cycle)
This commit is contained in:
@@ -3280,7 +3280,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T22:59:33.064313+00:00",
|
||||
"generatedAt": "2026-09-28T23:06:29.115221+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 165,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-28T23:05:26.349265+00:00",
|
||||
"generatedAt": "2026-09-28T23:07:48.063947+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-28T23:05:26.349265+00:00",
|
||||
"catalogUpdatedAt": "2026-09-28T23:07:48.063947+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-28T23:05:26.349265+00:00",
|
||||
"generatedAt": "2026-09-28T23:07:48.063947+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6449,6 +6449,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-28T23:05:26.349265+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-28T23:07:48.063947+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-28T21:58:57.842255+00:00",
|
||||
"lastSyncTime": "2026-09-28T21:58:57.568298+00:00",
|
||||
"generatedAt": "2026-09-28T23:06:29.026754+00:00",
|
||||
"lastSyncTime": "2026-09-28T23:06:28.764950+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3864,25 +3864,25 @@
|
||||
"decisionSuccessRate": 0.3636,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 42,
|
||||
"ambiguous_runtime": 43,
|
||||
"framework_architecture_unsupported": 11,
|
||||
"model_load": 3,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 61,
|
||||
"failureRate": 0.8841,
|
||||
"failureCount": 62,
|
||||
"failureRate": 0.8857,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 8,
|
||||
"successRate": 0.1159,
|
||||
"successRate": 0.1143,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 69,
|
||||
"unresolvedFailureCount": 46
|
||||
"total": 70,
|
||||
"unresolvedFailureCount": 47
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -6034,7 +6034,7 @@
|
||||
"decisionSuccessRate": 0.4167,
|
||||
"decisionTotal": 48,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 90,
|
||||
"ambiguous_runtime": 91,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"model_load": 5,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -6042,15 +6042,15 @@
|
||||
"参数/模板问题": 4,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 126,
|
||||
"failureRate": 0.863,
|
||||
"failureCount": 127,
|
||||
"failureRate": 0.8639,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 20,
|
||||
"successRate": 0.137,
|
||||
"total": 146,
|
||||
"unresolvedFailureCount": 97
|
||||
"successRate": 0.1361,
|
||||
"total": 147,
|
||||
"unresolvedFailureCount": 98
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 56,
|
||||
@@ -6153,7 +6153,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T21:58:57.829634+00:00",
|
||||
"generatedAt": "2026-09-28T23:06:29.013975+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6245,7 +6245,7 @@
|
||||
"decisionSuccessRate": 0.0891,
|
||||
"decisionTotal": 819,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 507,
|
||||
"ambiguous_runtime": 508,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 299,
|
||||
@@ -6258,15 +6258,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1611,
|
||||
"failureCount": 1612,
|
||||
"failureRate": 0.9567,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0433,
|
||||
"total": 1684,
|
||||
"unresolvedFailureCount": 849
|
||||
"total": 1685,
|
||||
"unresolvedFailureCount": 850
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -11241,6 +11241,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "spark2_5",
|
||||
"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-mlu|text-generation|spark2_5|fp8": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -34178,6 +34201,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"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-mlu|text-generation|spark2_5|fp8|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -51997,15 +52044,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17088,
|
||||
"totalRecords": 17309,
|
||||
"terminalRecords": 17089,
|
||||
"totalRecords": 17310,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6126,
|
||||
"decisionFailureRate": 0.8638,
|
||||
"decisionSuccessRate": 0.1362,
|
||||
"decisionTotal": 7092,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4435,
|
||||
"ambiguous_runtime": 4436,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -52021,15 +52068,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16122,
|
||||
"failureCount": 16123,
|
||||
"failureRate": 0.9435,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0565,
|
||||
"total": 17088,
|
||||
"unresolvedFailureCount": 9058
|
||||
"total": 17089,
|
||||
"unresolvedFailureCount": 9059
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -52058,7 +52105,6 @@
|
||||
"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 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。",
|
||||
"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 Kunlunxin_p-800|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 MetaX_c-500|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 Ascend_910-b4|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|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -52083,10 +52129,11 @@
|
||||
"组合 hygon_k100-ai|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 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 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 Vastai_va16|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 Vastai_va16|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|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": 17309,
|
||||
"summarizedRecords": 17310,
|
||||
"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": "9f7b660eb86b528e09122ca2f75f0d8a45fbb6c723aed58d396a76409af973e2",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "876bca10cd6efa10cadc44e192a9056cead12002294ecd856b397b85f33e2db9",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "835ac7584126ff112e7b24cd67b4d9be391cf778e79ef946805e40b344a5a2e3",
|
||||
".modelhub_state/official_capabilities.json": "923d42083677e8e253e81811ae44a7d9abecf03005c868d0c3bc5c0c7f46cc74",
|
||||
".modelhub_state/outcome_checkpoint.json": "2b3bb74b6feaff76851affc35c6cbcd7a90c9d6b42491c87ec80d8a9852c61e9",
|
||||
".modelhub_state/market_intelligence.json": "8ca11a033b12d76d8fac3fe6074a80f9b947230fa95f6c905f3bdc4102611ba2",
|
||||
".modelhub_state/official_capabilities.json": "c6e2c32e0e56d1446b3e0691e6ccc1276dc51ec1fc51bc7adfb73bcd22592f3d",
|
||||
".modelhub_state/outcome_checkpoint.json": "1a51ee4b7ecf57ba92d56e2a71322e0ff116887c39cdb9e61b9c043f0bc82bdc",
|
||||
".modelhub_state/queue_cleanup_latest.json": "1f4c42a37a5a4baa125d06463e6e0cfe425bb43e9871bb7096df76c3b33738fe",
|
||||
".modelhub_state/recent_outcomes.jsonl": "1f6ea975cd2deaf85a0cb3e87122886a82ce660a2c45914eb44108c20cd172e0",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "3e5b3abeff8e8bcd3ef925bd4c0c2200cbef458eb4c4523e6f453fe3c63b1980",
|
||||
".modelhub_state/recovery_intents.jsonl": "ffe55096718fd1efa719f71fa3a673795d01a67f6093a8d5a9da30f55b9c0b7e",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "4a16fcf147ca7256815faaf039cb9917bee787a0a1286afd7d59f0b161d37485",
|
||||
".modelhub_state/recovery_intents.jsonl": "9a2f3386d2cc5a4eb0036c2fd88588d94d4650b3612b19081a87cb3a740b4492",
|
||||
".modelhub_state/routing_intelligence.json": "2a22275a277723b1368e1f6dc16a13a645a993ad5ca7aacde4338523757c3c6e",
|
||||
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
|
||||
".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06",
|
||||
"ledger/submissions.jsonl": "4d9957d995a109b8d4450991e16066d058292b409c0aa70d15bff0444ec8180c",
|
||||
"outcomes/submissions.jsonl": "9a66c811a63456855359b6b8772dd61d63f917535a401ac2a0e16699745d8064"
|
||||
"outcomes/submissions.jsonl": "e04ed1aa1ca0b4f032c888136a281e8b8b45321522de76c2f75042a0a309a0a6"
|
||||
},
|
||||
"generation": 18118,
|
||||
"generation": 18119,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-28T23:05:27.140661+00:00",
|
||||
"updatedAt": "2026-09-28T23:07:52.455453+00:00",
|
||||
"writerId": "9d958b95ce4146c9939da0f14b9201ff"
|
||||
}
|
||||
|
||||
@@ -125,7 +125,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T13:43:30.144236+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "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": "2026-09-13T05:34:18.006195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4818284", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T17:57:25.416298+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "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": "2026-09-13T09:53:52.905331+00:00", "targetGpu": "MetaX_c-500", "taskId": "4823778", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T18:17:59.899586+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "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": "2026-09-13T10:16:13.410881+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4824251", "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_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}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-14T16:27:14.009107+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T08:26:23.557278+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4846122", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user