diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 7df4ca7d89..48177f9dc7 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-25T11:49:16.447283+00:00", + "generatedAt": "2026-10-25T11:50:54.139692+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 7a5f7c0aea..fabd9a55dc 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-25T11:45:04.359464+00:00", + "communityAttemptedAt": "2026-10-25T11:50:54.253317+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-25T11:49:16.560831+00:00", + "generatedAt": "2026-10-25T11:50:54.253317+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index e076a10fde..cae64e343f 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-25T11:49:16.560831+00:00", + "catalogUpdatedAt": "2026-10-25T11:50:54.253317+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-25T11:49:16.560831+00:00", + "generatedAt": "2026-10-25T11:50:54.253317+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6551,6 +6551,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-25T11:49:16.560831+00:00", + "taskTreeUpdatedAt": "2026-10-25T11:50:54.253317+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index f70f52b76e..d07844acbc 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-25T11:13:07.477192+00:00", - "lastSyncTime": "2026-10-25T11:13:07.247122+00:00", + "generatedAt": "2026-10-25T11:50:54.035949+00:00", + "lastSyncTime": "2026-10-25T11:50:53.757796+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -595,29 +595,29 @@ "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 55, - "decisionFailureRate": 0.9322, - "decisionSuccessRate": 0.0678, - "decisionTotal": 59, + "attributableFailureCount": 56, + "decisionFailureRate": 0.9333, + "decisionSuccessRate": 0.0667, + "decisionTotal": 60, "failureBreakdown": { "ambiguous_runtime": 99, "context_length": 9, - "framework_architecture_unsupported": 45, + "framework_architecture_unsupported": 46, "memory_capacity": 1, "platform_infrastructure": 1, "参数/模板问题": 43 }, - "failureCount": 198, - "failureRate": 0.9802, + "failureCount": 199, + "failureRate": 0.9803, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 4, - "successRate": 0.0198, + "successRate": 0.0197, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 202, + "total": 203, "unresolvedFailureCount": 142 }, "Ascend_910-b3|vllm|text-generation": { @@ -3356,15 +3356,15 @@ "unresolvedFailureCount": 491 }, "vllm_tokenizer_patch": { - "attributableFailureCount": 179, - "decisionFailureRate": 0.9471, - "decisionSuccessRate": 0.0529, - "decisionTotal": 189, + "attributableFailureCount": 180, + "decisionFailureRate": 0.9474, + "decisionSuccessRate": 0.0526, + "decisionTotal": 190, "failureBreakdown": { "ambiguous_runtime": 221, "backend_operator": 17, "context_length": 10, - "framework_architecture_unsupported": 116, + "framework_architecture_unsupported": 117, "memory_capacity": 2, "model_load": 26, "platform_infrastructure": 3, @@ -3373,28 +3373,28 @@ "tokenizer_compatibility": 2, "参数/模板问题": 137 }, - "failureCount": 540, - "failureRate": 0.9818, + "failureCount": 541, + "failureRate": 0.9819, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, - "successRate": 0.0182, - "total": 550, + "successRate": 0.0181, + "total": 551, "unresolvedFailureCount": 358 } }, - "generatedAt": "2026-10-25T11:13:07.462992+00:00", + "generatedAt": "2026-10-25T11:50:54.020807+00:00", "gpuSummaries": { "Ascend_910-b3": { - "attributableFailureCount": 133, - "decisionFailureRate": 0.8581, - "decisionSuccessRate": 0.1419, - "decisionTotal": 155, + "attributableFailureCount": 134, + "decisionFailureRate": 0.859, + "decisionSuccessRate": 0.141, + "decisionTotal": 156, "failureBreakdown": { "ambiguous_runtime": 168, "context_length": 9, - "framework_architecture_unsupported": 116, + "framework_architecture_unsupported": 117, "memory_capacity": 2, "model_load": 2, "platform_infrastructure": 1, @@ -3404,14 +3404,14 @@ "日志缺失": 3, "验证失败": 27 }, - "failureCount": 407, - "failureRate": 0.9487, + "failureCount": 408, + "failureRate": 0.9488, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0513, - "total": 429, + "successRate": 0.0512, + "total": 430, "unresolvedFailureCount": 273 }, "Ascend_910-b4": { @@ -4542,14 +4542,14 @@ "unresolvedFailureCount": 9 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|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_tokenizer_patch", "modelType": "plamo3", @@ -4561,7 +4561,7 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 1, + "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|prism_hadamard_qwen35|none": { @@ -29818,6 +29818,30 @@ "total": 3, "unresolvedFailureCount": 3 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|none|30": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 30, + "modelType": "plamo3", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b3", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -62405,20 +62429,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18075, - "totalRecords": 18619, + "terminalRecords": 18076, + "totalRecords": 18620, "totals": { - "attributableFailureCount": 6380, - "decisionFailureRate": 0.8661, - "decisionSuccessRate": 0.1339, - "decisionTotal": 7366, + "attributableFailureCount": 6381, + "decisionFailureRate": 0.8662, + "decisionSuccessRate": 0.1338, + "decisionTotal": 7367, "failureBreakdown": { "ambiguous_runtime": 4695, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, "context_length": 328, - "framework_architecture_unsupported": 2369, + "framework_architecture_unsupported": 2370, "memory_capacity": 1207, "model_load": 582, "platform_infrastructure": 972, @@ -62429,14 +62453,14 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17089, - "failureRate": 0.9454, + "failureCount": 17090, + "failureRate": 0.9455, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, - "successRate": 0.0546, - "total": 18075, + "successRate": 0.0545, + "total": 18076, "unresolvedFailureCount": 9737 }, "warnings": [ @@ -62500,6 +62524,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18619, + "summarizedRecords": 18620, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 26e36db445..75bd664c65 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3829,6 +3829,18 @@ {"batchId": "d5ffd1fae5614e72a8e450837a95e11d", "completedAt": "2026-10-25T11:04:03.803164+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:04:01.501370+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c3ddba5ad4a64c24bad914158e1c1434", "lastModified": "2026-10-22T14:14:09+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5-FP8", "reason": null, "reconciledAt": "2026-10-25T11:49:22.381968+00:00", "repoId": "InternScience/Sage-A1.5-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5779345", "taskType": "text-generation"} {"batchId": "c918fe1d1c804b44b9b9622346649069", "completedAt": "2026-10-25T11:39:23.084103+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:39:20.554410+00:00", "framework": "vllm-mlu", "intentId": "a95659c861c343ae88fbebf4f0da849f", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T11:49:22.381550+00:00", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5780290", "taskType": "text-generation"} {"batchId": "0023e4bfbff04839ab4f796fcd1369f4", "completedAt": "2026-10-25T11:46:50.711922+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:46:48.387965+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6d46cb6a64a64fa78a01c7b6e8f2ea94", "lastModified": "2026-10-21T17:21:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "reason": null, "reconciledAt": "2026-10-25T11:49:22.383723+00:00", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5780488", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191330+00:00", "framework": "vllm-mlu", "intentId": "fc92e3b2d39840f7a0a3ae9d037e244c", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191466+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ee64864895d64f5995802d3d2c8efeec", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-AWQ-4bit", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191517+00:00", "framework": "vllm_fix_tokenizer", "intentId": "426311e2b44d4756aa993acf58a6662c", "lastModified": "2026-10-21T16:41:42+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191562+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a3954aa88f594692a444eef3a1090fab", "lastModified": "2026-10-25T11:26:46+00:00", "modelAddress": "https://modelscope.cn/models/ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "repoId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191607+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d67f51c4ad1443189283f4fc28eeaabc", "lastModified": "2026-10-24T12:36:06+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191651+00:00", "framework": "vllm_fix_tokenizer", "intentId": "291e11ab75c24ca5908614bd8c8d6586", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191696+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ea84cc36798341f9b1c4ca6a11a592b7", "lastModified": "2026-10-21T17:16:44+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191740+00:00", "framework": "vllm_fix_tokenizer", "intentId": "80072c6d9c014a318699a1e08b2eea6e", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191784+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ffdba76e745844fd926b2e0733c840a6", "lastModified": "2026-10-21T16:18:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191827+00:00", "framework": "vllm_fix_tokenizer", "intentId": "58a8c21de576493ba6da4ac75e10faf6", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191871+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3a7b6c94809746488feca70e546a4e3f", "lastModified": "2026-10-24T13:56:05+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "23f1c7911a4a401a9f0dbf1b6b56be83", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:50:55.191914+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c6762cacb154acb806e45e28020c8b7", "lastModified": "2026-10-21T16:25:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-4bit", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "b1b1d0cd8fb54fabad70b12dbbb0e9a2", "completedAt": "2026-10-25T11:49:19.866783+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:49:17.310207+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d3c1355aeb4e43ba9b9c4f5f3ecf276a", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "b1b1d0cd8fb54fabad70b12dbbb0e9a2", "completedAt": "2026-10-25T11:49:19.866781+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:49:17.310156+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5d02af1c1bc049f4962b480081635c5d", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "b1b1d0cd8fb54fabad70b12dbbb0e9a2", "completedAt": "2026-10-25T11:49:19.866777+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T11:49:17.310114+00:00", "framework": "vllm_fix_tokenizer", "intentId": "735bcf50a57a4f7a906416d55000ab3c", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index b91010f3ff..3d93e64183 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "f431d24062e520e3309dc73e7df89f3681e81f743c9dc924f6e00480b0dccb44", - ".modelhub_state/architecture_compatibility_blacklist.json": "f79280369a61a02656518b167f04adc874eae5bb9eadb1fb89c20a25c7a86e87", + ".modelhub_state/architecture_compatibility_blacklist.json": "9052f7e5dc50bb1becb91115e98d9cb047eee3bd373dfeee7d4b00675ed64552", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "a3ec196ddfe88bc0cfc9737472811ce5cc31b715a5a1c00ee65a6fccf6b6ed1c", - ".modelhub_state/official_capabilities.json": "c6dfbd621ed95a7a7168d5dadc0fd0a4daa76c9349017c478198114f63d20e6d", - ".modelhub_state/outcome_checkpoint.json": "a8c45b807334574fa9e3a024c6137335fd4562ac32a2684b1ad4f641c6609e08", + ".modelhub_state/market_intelligence.json": "d3b606ae44bb79dced1edb090c07092351346ae5ef9536ca8e5ff6edfa322e78", + ".modelhub_state/official_capabilities.json": "005ac7ee809d4ee6a22f8537332f30373ef7f65857426bab736e683a00a84677", + ".modelhub_state/outcome_checkpoint.json": "6c26a4985beb21cbe6965ee8434228b62d60cea62fd93b467aaba7670bfa8240", ".modelhub_state/queue_cleanup_latest.json": "85ae46090642cadafa2c4d59b957edc6694770417a3b93e0d070da0f91189bef", ".modelhub_state/recent_outcomes.jsonl": "fc9368e1c98536f77838d20a3ed28011974beb3b61f7f86cdb4f4a2847aa5e5d", ".modelhub_state/recovery_active_tasks.jsonl": "823c35db58e8806dd1e0de2154127923eb3a337f2aabfa8c90c796250adaa97a", - ".modelhub_state/recovery_intents.jsonl": "70ce2aaee3bb9d93893b233e219bac45df7b5bb9f9e51436aadfde4abc3455cf", + ".modelhub_state/recovery_intents.jsonl": "83b0ceb235665f80d42a5ebb4f4d9ccbfe70f9200d97a89eb9ba198f9edb06ae", ".modelhub_state/routing_intelligence.json": "f3d1539437d7bd4c47eec5c23dd35df98bb9f8c43d2209c8c2111c3d6ea1bf1e", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/worker_crashes.jsonl": "3527d86c4fe5a43e8c0b1158e6f24e748474fce5a149c696caf4a1da895ac64a", "ledger/submissions.jsonl": "0873231928321b33235a4c65e76a0ec9603bbf235ff3268d4f80a4b2db8647ec", - "outcomes/submissions.jsonl": "0355c9907907f163001a7425384f4647f9ba63f0f1347ed0464810a0d959dd33" + "outcomes/submissions.jsonl": "f8b8bf7df7c58946467f04ea6c79f7b48972435691ce93510c13c8ce7ba7a51f" }, - "generation": 36225, - "phase": "cycle", + "generation": 36226, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-25T11:49:22.587925+00:00", + "updatedAt": "2026-10-25T11:50:55.374347+00:00", "writerId": "750e06ff79b245419d079bcf827fbb45" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 1104e2a8db..5014f8d2ce 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -270,7 +270,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253639+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.154928+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260094", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253471+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.161002+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260095", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253604+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.356198+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260103", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253465+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.464366+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260105", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253493+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.565606+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260116", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253414+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.563992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260111", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253459+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.674309+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260118", "taskType": "text-generation", "verifyResult": null} @@ -1086,7 +1085,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T10:30:27.654205+00:00", "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T02:30:10.729769+00:00", "targetGpu": "MetaX_c-500", "taskId": "5771004", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T10:53:31.443485+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T02:52:51.832672+00:00", "targetGpu": "MetaX_c-500", "taskId": "5771333", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T11:13:07.247098+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T03:12:43.268661+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5771609", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 11.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10652397737, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 10652397737}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T03:50:00.659747+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5772051", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T11:50:53.757774+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 11.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10652397737, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 10652397737}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T03:50:00.659747+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5772051", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619082384, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19619082384}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T04:54:28.450141+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5772869", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064344108, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064344108}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T05:43:05.936199+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5773637", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8883470152, "estimatedRequiredGiB": 9.951, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8903670650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9409813744, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.5", "custom_tag:code", "custom_tag:agent", "custom_tag:sft", "custom_tag:omnicoder", "custom_tag:tesslate"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8903670650}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T05:58:44.334550+00:00", "targetGpu": "Vastai_va16", "taskId": "5773873", "taskType": "text-generation", "verifyResult": null}