state: generation 7460 (cycle)

This commit is contained in:
2026-09-15 01:08:15 +00:00
parent d96aa23544
commit 5ddd70e940
9 changed files with 2203 additions and 2135 deletions

View File

@@ -1558,7 +1558,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T01:04:25.009489+00:00",
"generatedAt": "2026-09-15T01:08:14.934590+00:00",
"summary": {
"activeBlockCount": 77,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 541,
"listingErrors": 542,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-15T01:04:24.977957+00:00",
"updatedAt": "2026-09-15T01:08:14.908434+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T01:02:34.659888+00:00",
"generatedAt": "2026-09-15T01:05:38.589398+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-15T00:56:25.975339+00:00",
"lastSyncTime": "2026-09-15T00:56:25.725574+00:00",
"generatedAt": "2026-09-15T01:05:26.121051+00:00",
"lastSyncTime": "2026-09-15T01:05:25.842376+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2144,10 +2144,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 41,
"ambiguous_runtime": 42,
"参数/模板问题": 2
},
"failureCount": 43,
"failureCount": 44,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2157,8 +2157,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 43,
"unresolvedFailureCount": 43
"total": 44,
"unresolvedFailureCount": 44
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2183,30 +2183,30 @@
"unresolvedFailureCount": 57
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 56,
"decisionFailureRate": 0.9333,
"decisionSuccessRate": 0.0667,
"decisionTotal": 60,
"attributableFailureCount": 57,
"decisionFailureRate": 0.9344,
"decisionSuccessRate": 0.0656,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 27,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 9
},
"failureCount": 76,
"failureRate": 0.95,
"failureCount": 77,
"failureRate": 0.9506,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.05,
"successRate": 0.0494,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 80,
"total": 81,
"unresolvedFailureCount": 20
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2600,14 +2600,14 @@
"unresolvedFailureCount": 892
},
"vllm": {
"attributableFailureCount": 326,
"attributableFailureCount": 327,
"decisionFailureRate": 0.9879,
"decisionSuccessRate": 0.0121,
"decisionTotal": 330,
"decisionTotal": 331,
"failureBreakdown": {
"ambiguous_runtime": 216,
"backend_operator": 34,
"framework_architecture_unsupported": 237,
"framework_architecture_unsupported": 238,
"memory_capacity": 7,
"model_load": 27,
"platform_infrastructure": 1,
@@ -2616,14 +2616,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 30
},
"failureCount": 573,
"failureCount": 574,
"failureRate": 0.9931,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0069,
"total": 577,
"total": 578,
"unresolvedFailureCount": 246
},
"vllm-mlu": {
@@ -2695,7 +2695,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 43,
"ambiguous_runtime": 44,
"backend_operator": 2,
"framework_architecture_unsupported": 8,
"model_load": 1,
@@ -2703,15 +2703,15 @@
"tokenizer_compatibility": 42,
"参数/模板问题": 8
},
"failureCount": 108,
"failureCount": 109,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 0,
"successRate": 0.0,
"total": 108,
"unresolvedFailureCount": 51
"total": 109,
"unresolvedFailureCount": 52
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2732,7 +2732,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T00:56:25.968195+00:00",
"generatedAt": "2026-09-15T01:05:26.115861+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 39,
@@ -2927,44 +2927,44 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 84,
"ambiguous_runtime": 85,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 110,
"failureCount": 111,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 110,
"unresolvedFailureCount": 109
"total": 111,
"unresolvedFailureCount": 110
},
"MetaX_c-500": {
"attributableFailureCount": 56,
"decisionFailureRate": 0.8116,
"decisionSuccessRate": 0.1884,
"decisionTotal": 69,
"attributableFailureCount": 57,
"decisionFailureRate": 0.8143,
"decisionSuccessRate": 0.1857,
"decisionTotal": 70,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 27,
"framework_architecture_unsupported": 20,
"framework_architecture_unsupported": 21,
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 18,
"验证失败": 48
},
"failureCount": 133,
"failureRate": 0.911,
"failureCount": 134,
"failureRate": 0.9116,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.089,
"total": 146,
"successRate": 0.0884,
"total": 147,
"unresolvedFailureCount": 77
},
"Mthreads_s4000": {
@@ -4255,6 +4255,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -4692,14 +4715,14 @@
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "rwkv7",
@@ -4711,7 +4734,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|spark2_5|none": {
@@ -7526,6 +7549,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -8291,6 +8338,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|rwkv7|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|rwkv7|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -9012,17 +9083,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1883,
"totalRecords": 1976,
"terminalRecords": 1885,
"totalRecords": 1978,
"totals": {
"attributableFailureCount": 572,
"decisionFailureRate": 0.9008,
"decisionSuccessRate": 0.0992,
"decisionTotal": 635,
"attributableFailureCount": 573,
"decisionFailureRate": 0.9009,
"decisionSuccessRate": 0.0991,
"decisionTotal": 636,
"failureBreakdown": {
"ambiguous_runtime": 453,
"ambiguous_runtime": 454,
"backend_operator": 44,
"framework_architecture_unsupported": 367,
"framework_architecture_unsupported": 368,
"memory_capacity": 12,
"model_load": 78,
"platform_infrastructure": 6,
@@ -9032,15 +9103,15 @@
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1820,
"failureRate": 0.9665,
"failureCount": 1822,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 63,
"successRate": 0.0335,
"total": 1883,
"unresolvedFailureCount": 1242
"successRate": 0.0334,
"total": 1885,
"unresolvedFailureCount": 1243
},
"warnings": [
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
@@ -9078,6 +9149,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1976,
"summarizedRecords": 1978,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "10a24da6f0625f0a9cfd56df256ad2e1b7fcfb6ab2013c59b7c105df1daa049f",
".modelhub_state/architecture_history_backfill.json": "27397d9cb22de13059042e02c9d5c5709fa577c5e3789a013be6eb7994e4e32a",
".modelhub_state/market_intelligence.json": "96017edcb035accc50d4f208bcffd2414bec044a686f6dd5f1fc9d4614284254",
".modelhub_state/official_capabilities.json": "4153b3bea986a9a98d5913f26d1607c9d3fb402fff024fce6a8d4ad777598ec7",
".modelhub_state/outcome_checkpoint.json": "7f1bb009a807f7cef48875c93329735dfeb69a533070d20fbce4ebf2fd1e1bea",
".modelhub_state/architecture_compatibility_blacklist.json": "3950db65cabdaa83921c81140eea5cda629922658b6750fbb372e91f452a19e7",
".modelhub_state/architecture_history_backfill.json": "c0c17f80ee0f96751cbf47ac0e49add31df45c1a3f26cff7b2549011c0694281",
".modelhub_state/market_intelligence.json": "6829d51b46521d893684bb5d62bf87f8bba55a3b6bff7599e1e8f7ca1a1d88f9",
".modelhub_state/official_capabilities.json": "0ea7d8cfa8a2e4ad8103729393e73942d8c54c4ed998c24bcf6d48daf0f0f4dd",
".modelhub_state/outcome_checkpoint.json": "8295c5b9b377024b7181944659a746e7ed14a5dc046667cad44deeb956fddc82",
".modelhub_state/queue_cleanup_latest.json": "01e08fd4618eb925c85708b1e84308d8914f762fc7ce784e5b71b8af21bef866",
".modelhub_state/recent_outcomes.jsonl": "3e8d801148445805885cddedefff9377d42f0ef9bd4a9fce13d78d2cc48cad45",
".modelhub_state/recovery_active_tasks.jsonl": "bfda39887d851127535a59653638c58e0b45e19bd796c27f4cb333d9c60165ca",
".modelhub_state/recovery_intents.jsonl": "a740e9bfd450a4da65ccad11de25b06797eff15f905f3a4407204bb2225f6f51",
".modelhub_state/recovery_active_tasks.jsonl": "c4b2f64d98555d953d832777dbea386167fb2b55e30659b3363c2a05b37bff0c",
".modelhub_state/recovery_intents.jsonl": "65b03473ccb4027eb76851bc0df94285239dfaf4fbad09605b4fc510aa9b0762",
".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "b8563512d893ae2a4f8a4d65881d0eab34d0b8d937550ac1fd54cdbaddb9db2b",
"outcomes/submissions.jsonl": "8fb1bca3e421116716deccb3142261e8474705ab5a5757dca848881a4970c52a"
"outcomes/submissions.jsonl": "f4ed91bea5b07a457e46fd7cf22547de9a6aa325849b2f7498b03820d952bc42"
},
"generation": 7459,
"generation": 7460,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-15T01:04:25.141072+00:00",
"updatedAt": "2026-09-15T01:08:15.672974+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
}

View File

@@ -146,14 +146,12 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-06T16:36:18.900122+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:34:09.456899+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4664143", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T17:08:48.403518+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T09:06:12.932838+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4664478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T17:46:47.144783+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T09:46:33.145376+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4664976", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T18:28:08.305021+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T10:24:50.148662+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665474", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T18:28:08.305046+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T10:24:50.144356+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4665470", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T20:39:29.797774+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T12:37:22.515030+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4667091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613082+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679222028, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679222028}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.194804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613054+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72656575880, "estimatedRequiredGiB": 81.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72665883326, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72665883326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613090+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:01:57.388649+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399880+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407871+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "verifyResult": null}