state: generation 7522 (cycle)

This commit is contained in:
2026-09-15 04:22:15 +00:00
parent 64ba97ced4
commit 4a0871277a
10 changed files with 2119 additions and 2076 deletions

View File

@@ -1564,7 +1564,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T04:19:02.105600+00:00",
"generatedAt": "2026-09-15T04:22:14.440231+00:00",
"summary": {
"activeBlockCount": 77,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 546,
"listingErrors": 547,
"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": "2026-09-15T04:19:02.078710+00:00",
"updatedAt": "2026-09-15T04:22:14.414917+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T04:16:28.679045+00:00",
"generatedAt": "2026-09-15T04:20:11.525115+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": "2026-09-15T03:29:11.407341+00:00",
"lastSyncTime": "2026-09-15T03:29:11.202359+00:00",
"generatedAt": "2026-09-15T04:20:02.919899+00:00",
"lastSyncTime": "2026-09-15T04:20:02.843280+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1774,24 +1774,24 @@
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"failureBreakdown": {
"framework_architecture_unsupported": 6,
"model_load": 1
},
"failureCount": 7,
"failureRate": 1.0,
"failureRate": 0.875,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.125,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2608,9 +2608,9 @@
},
"vllm": {
"attributableFailureCount": 332,
"decisionFailureRate": 0.9852,
"decisionSuccessRate": 0.0148,
"decisionTotal": 337,
"decisionFailureRate": 0.9822,
"decisionSuccessRate": 0.0178,
"decisionTotal": 338,
"failureBreakdown": {
"ambiguous_runtime": 216,
"backend_operator": 34,
@@ -2624,13 +2624,13 @@
"参数/模板问题": 30
},
"failureCount": 579,
"failureRate": 0.9914,
"failureRate": 0.9897,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 5,
"successRate": 0.0086,
"total": 584,
"successCount": 6,
"successRate": 0.0103,
"total": 585,
"unresolvedFailureCount": 246
},
"vllm-mlu": {
@@ -2739,7 +2739,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T03:29:11.402588+00:00",
"generatedAt": "2026-09-15T04:20:02.915503+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 39,
@@ -2791,9 +2791,9 @@
},
"Biren_166m": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.9512,
"decisionSuccessRate": 0.0488,
"decisionTotal": 41,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
@@ -2805,13 +2805,13 @@
"验证失败": 27
},
"failureCount": 98,
"failureRate": 0.98,
"failureRate": 0.9703,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.02,
"total": 100,
"successCount": 3,
"successRate": 0.0297,
"total": 101,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3161,6 +3161,27 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -6022,6 +6043,28 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen2|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -9253,13 +9296,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1897,
"totalRecords": 1990,
"terminalRecords": 1898,
"totalRecords": 1991,
"totals": {
"attributableFailureCount": 581,
"decisionFailureRate": 0.8994,
"decisionSuccessRate": 0.1006,
"decisionTotal": 646,
"decisionFailureRate": 0.898,
"decisionSuccessRate": 0.102,
"decisionTotal": 647,
"failureBreakdown": {
"ambiguous_runtime": 456,
"backend_operator": 44,
@@ -9274,13 +9317,13 @@
"验证失败": 673
},
"failureCount": 1832,
"failureRate": 0.9657,
"failureRate": 0.9652,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 65,
"successRate": 0.0343,
"total": 1897,
"successCount": 66,
"successRate": 0.0348,
"total": 1898,
"unresolvedFailureCount": 1245
},
"warnings": [
@@ -9319,6 +9362,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1990,
"summarizedRecords": 1991,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -621,7 +621,6 @@
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "modelId": "hcnote/SparkMuse-4B", "submitTime": "2026-09-14T20:04:19.314042+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4856588", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "submitTime": "2026-09-14T20:04:19.387527+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856586", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "modelId": "hcnote/SparkMuse-4B", "submitTime": "2026-09-14T20:23:33.974791+00:00", "targetGpu": "MetaX_c-500", "taskId": "4856813", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "submitTime": "2026-09-14T20:36:23.395422+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856934", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "modelId": "hcnote/SparkMuse-4B", "submitTime": "2026-09-14T20:41:43.211677+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857006", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B", "modelId": "hcnote/SparkMuse-4B", "submitTime": "2026-09-14T20:59:57.940217+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857211", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "submitTime": "2026-09-14T21:09:06.637418+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4857320", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
@@ -642,6 +641,7 @@
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "submitTime": "2026-09-14T19:47:58.577906+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856415", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "submitTime": "2026-09-14T20:04:19.385502+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856587", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "submitTime": "2026-09-14T20:21:39.119992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "submitTime": "2026-09-14T20:36:23.395422+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4856934", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-08T23:02:51.933574+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729525", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-08T23:02:51.939534+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729523", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-08T23:02:52.096464+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729531", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "585133da440c46a33d27daeb38e6eca53909b565b760a0240632cedb44abfbbc",
".modelhub_state/architecture_history_backfill.json": "6e1ba3cfbe4553ce0d6c3a1f8b035187713c7cf9166b0227ffd61c51c53bc69c",
".modelhub_state/market_intelligence.json": "505276c9c3d904edd2fe5520ddc7e579a70f72acdf1fa6731353472389a57e41",
".modelhub_state/official_capabilities.json": "abc7d6957bbd75ab92c0a86d8cecc83b6b1660e0e277d4105c970d8e2a70c82e",
".modelhub_state/outcome_checkpoint.json": "90820e51e71a23dd046e0510016ee6ce92a17f491f3c7a4a360fb37f5303b22f",
".modelhub_state/architecture_compatibility_blacklist.json": "fcc70c30000940a7a0eddab21325a0f0274e77fc3a63070e0bed2500cab02578",
".modelhub_state/architecture_history_backfill.json": "0f67e65826adc4ac6c993f3d0055cb39a18fc24d1647d2bcd3e4e851a8f29230",
".modelhub_state/market_intelligence.json": "2529dd2cf1f016c0ca61fa56d96eee859ae6dc57b966502af03de2bb382959db",
".modelhub_state/official_capabilities.json": "2544a009c2e94c97fa4bca0c53134269b26fa32af316df5d9b02d710ad6ea57e",
".modelhub_state/outcome_checkpoint.json": "d6649db08add82e0d37b42f5054108d2ceeac3c57b054398bf0485377ea71dc5",
".modelhub_state/queue_cleanup_latest.json": "01e08fd4618eb925c85708b1e84308d8914f762fc7ce784e5b71b8af21bef866",
".modelhub_state/recent_outcomes.jsonl": "8c10e9584b43e903283b39313edc69e112740cef227cada912e9318b4717c5ff",
".modelhub_state/recovery_active_tasks.jsonl": "2d0c19c21270aed7096e90f4474a6b6b6ea22440b6367561add06b35da3be346",
".modelhub_state/recovery_intents.jsonl": "dffcefbc7ded751caa707ffa78f07f7d984f1810550c7c1e7f89071bcaeb263f",
".modelhub_state/recovery_active_tasks.jsonl": "88c58af4f5e2a378b0941d5e95982def262439d6baa149732865a63fa4411257",
".modelhub_state/recovery_intents.jsonl": "ff97773aaa269cc04a385b619aab5cd84767827379de4507645c1939d7a54d42",
".modelhub_state/routing_intelligence.json": "1f0b19a6ee9315cdcc67bf891fde115ed50d59d35f922358b48245c520476b85",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "018a9c6f5fc6a1e1a7212cdeb4b83e9f655deb359b2427472d82332662d6fc50",
"outcomes/submissions.jsonl": "caa05bef33fb1a06f4aecc300d671b4ad2535e1539ae7afa949fc6332a6db193"
"ledger/submissions.jsonl": "2d190e618abd879c9e1c01e63277c27460ea38ae0187c41bbcb60f8191e2d425",
"outcomes/submissions.jsonl": "bf83f361f4b15e959262917423b6bf79adf57b5cf7f5887777109fad63026a97"
},
"generation": 7521,
"generation": 7522,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-15T04:19:02.213900+00:00",
"updatedAt": "2026-09-15T04:22:15.069292+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
}

View File

@@ -203,7 +203,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903599+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.516825+00:00", "targetGpu": "Biren_166m", "taskId": "4713224", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903621+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "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": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.345690+00:00", "targetGpu": "Biren_166m", "taskId": "4713233", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903627+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "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": 4465562659, "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": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.160342+00:00", "targetGpu": "Biren_166m", "taskId": "4713232", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903639+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.169874+00:00", "targetGpu": "Biren_166m", "taskId": "4713231", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T15:30:55.706707+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:30:11.995863+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4713445", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T17:15:48.506915+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426226990, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:15:31.168687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4715997", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T17:52:18.933025+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:42:38.119885+00:00", "targetGpu": "Vastai_va16", "taskId": "4716367", "taskType": "text-generation", "verifyResult": null}