diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 258fed21d1..23544de7a4 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-25T04:14:45.837316+00:00", + "generatedAt": "2026-10-25T04:16:24.042438+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index af2914f760..2471404c64 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-25T04:14:45.961543+00:00", + "generatedAt": "2026-10-25T04:16:24.174604+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index c5d4470431..e7b71d0298 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-25T04:14:45.961543+00:00", + "catalogUpdatedAt": "2026-10-25T04:16:24.174604+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-25T04:14:46.564269+00:00", + "generatedAt": "2026-10-25T04:16:24.560075+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -1099,19 +1099,11 @@ ], "updatedAt": "2026-10-25T04:12:59.314718+00:00" }, - "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-Base|2026-10-24T12:07:57+00:00|Ascend_910-b4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-10-25T04:07:39.574206+00:00" - }, "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-Base|2026-10-24T12:07:57+00:00|Biren_166m": { "taskTypes": [ "text-generation" ], - "updatedAt": "2026-10-25T04:07:39.534007+00:00" + "updatedAt": "2026-10-25T04:16:24.560075+00:00" }, "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-Base|2026-10-24T12:07:57+00:00|Cambricon_mlu-370-x4": { "taskTypes": [ @@ -1137,6 +1129,15 @@ ], "updatedAt": "2026-10-25T04:09:42.398556+00:00" }, + "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-Base|2026-10-24T12:07:57+00:00|Iluvatar_mrv-100": { + "taskTypes": [ + "asr", + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-10-25T04:16:24.447079+00:00" + }, "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-Base|2026-10-24T12:07:57+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -6321,6 +6322,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-25T04:14:45.961543+00:00", + "taskTreeUpdatedAt": "2026-10-25T04:16:24.174604+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index f9a4419982..c490045216 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-25T04:14:45.733253+00:00", - "lastSyncTime": "2026-10-25T04:14:45.438309+00:00", + "generatedAt": "2026-10-25T04:16:23.942455+00:00", + "lastSyncTime": "2026-10-25T04:16:23.645922+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2337,19 +2337,19 @@ "unresolvedFailureCount": 66 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 12, + "attributableFailureCount": 13, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 12, + "decisionTotal": 13, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 2, "context_length": 1, "framework_architecture_unsupported": 7, - "model_load": 2, + "model_load": 3, "参数/模板问题": 42 }, - "failureCount": 55, + "failureCount": 56, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -2359,7 +2359,7 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 55, + "total": 56, "unresolvedFailureCount": 43 }, "MetaX_c-500|vllm|feature_emb": { @@ -3356,35 +3356,35 @@ "unresolvedFailureCount": 487 }, "vllm_tokenizer_patch": { - "attributableFailureCount": 178, - "decisionFailureRate": 0.9468, - "decisionSuccessRate": 0.0532, - "decisionTotal": 188, + "attributableFailureCount": 179, + "decisionFailureRate": 0.9471, + "decisionSuccessRate": 0.0529, + "decisionTotal": 189, "failureBreakdown": { "ambiguous_runtime": 218, "backend_operator": 17, "context_length": 10, "framework_architecture_unsupported": 116, "memory_capacity": 2, - "model_load": 25, + "model_load": 26, "platform_infrastructure": 3, "repository_structure": 3, "runtime_memory": 3, "tokenizer_compatibility": 2, "参数/模板问题": 135 }, - "failureCount": 534, - "failureRate": 0.9816, + "failureCount": 535, + "failureRate": 0.9817, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, - "successRate": 0.0184, - "total": 544, + "successRate": 0.0183, + "total": 545, "unresolvedFailureCount": 353 } }, - "generatedAt": "2026-10-25T04:14:45.718451+00:00", + "generatedAt": "2026-10-25T04:16:23.923910+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3660,10 +3660,10 @@ "unresolvedFailureCount": 170 }, "MetaX_c-500": { - "attributableFailureCount": 688, - "decisionFailureRate": 0.824, - "decisionSuccessRate": 0.176, - "decisionTotal": 835, + "attributableFailureCount": 689, + "decisionFailureRate": 0.8242, + "decisionSuccessRate": 0.1758, + "decisionTotal": 836, "failureBreakdown": { "ambiguous_runtime": 308, "architecture_compatibility": 21, @@ -3671,7 +3671,7 @@ "context_length": 60, "framework_architecture_unsupported": 215, "memory_capacity": 85, - "model_load": 67, + "model_load": 68, "platform_infrastructure": 5, "repository_structure": 114, "runtime_memory": 2, @@ -3680,14 +3680,14 @@ "日志缺失": 15, "验证失败": 48 }, - "failureCount": 1522, - "failureRate": 0.9119, + "failureCount": 1523, + "failureRate": 0.912, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 147, - "successRate": 0.0881, - "total": 1669, + "successRate": 0.088, + "total": 1670, "unresolvedFailureCount": 829 }, "Mthreads_s4000": { @@ -20041,14 +20041,15 @@ "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors": { - "attributableFailureCount": 0, - "decisionFailureRate": 0.0, + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 0, + "decisionTotal": 1, "failureBreakdown": { + "model_load": 1, "参数/模板问题": 2 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "k2_horizon", @@ -20060,7 +20061,7 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 2, + "total": 3, "unresolvedFailureCount": 2 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|none": { @@ -53424,14 +53425,15 @@ "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|32": { - "attributableFailureCount": 0, - "decisionFailureRate": 0.0, + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 0, + "decisionTotal": 1, "failureBreakdown": { + "model_load": 1, "参数/模板问题": 1 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, @@ -53444,7 +53446,7 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 1, + "total": 2, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": { @@ -62194,13 +62196,13 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18054, - "totalRecords": 18598, + "terminalRecords": 18055, + "totalRecords": 18599, "totals": { - "attributableFailureCount": 6376, + "attributableFailureCount": 6377, "decisionFailureRate": 0.8661, "decisionSuccessRate": 0.1339, - "decisionTotal": 7362, + "decisionTotal": 7363, "failureBreakdown": { "ambiguous_runtime": 4686, "architecture_compatibility": 212, @@ -62209,7 +62211,7 @@ "context_length": 328, "framework_architecture_unsupported": 2369, "memory_capacity": 1207, - "model_load": 578, + "model_load": 579, "platform_infrastructure": 972, "repository_structure": 742, "runtime_memory": 101, @@ -62218,20 +62220,21 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17068, + "failureCount": 17069, "failureRate": 0.9454, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0546, - "total": 18054, + "total": 18055, "unresolvedFailureCount": 9720 }, "warnings": [ "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", @@ -62239,9 +62242,8 @@ "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -62289,6 +62291,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18598, + "summarizedRecords": 18599, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index a42b87043a..efe217ad75 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3810,6 +3810,18 @@ {"batchId": "a3600559e38849dab8a537b39bd6c6b7", "completedAt": "2026-10-25T02:52:53.138378+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T02:52:50.883782+00:00", "framework": "vllm_tokenizer_patch", "intentId": "25dc79da915e45ffa87ae1c4aa1d37d2", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "reason": null, "reconciledAt": "2026-10-25T04:14:52.199643+00:00", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5771333", "taskType": "text-generation"} {"batchId": "3847981ede0c44208ee957b63c7529ab", "completedAt": "2026-10-25T03:12:44.632876+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T03:12:42.283230+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cefc269bf0bf4509a434e70429166d48", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T04:14:52.199342+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5771609", "taskType": "text-generation"} {"batchId": "c2f0892325ba48a0911df4438b19ac90", "completedAt": "2026-10-25T03:50:03.824728+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T03:49:58.711717+00:00", "framework": "vllm_tokenizer_patch", "intentId": "598d845f0b0e48c4b68b25e922a1ee0f", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T04:14:52.201440+00:00", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5772051", "taskType": "text-generation"} +{"batchId": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075559+00:00", "framework": "vllm_fix_tokenizer", "intentId": "501ff0213049440195846d17f2841abb", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075675+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96b6ef05ba424cb38f8e1b7a1845c0eb", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075723+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ae676dfd45924e5697ff895e4dc8e5d8", "lastModified": "2026-10-24T00:34:29+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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075766+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a7f760258a5545fc87d1a4f9cf2fd0f7", "lastModified": "2026-10-21T17:13:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-4bit", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075808+00:00", "framework": "vllm_fix_tokenizer", "intentId": "445fb9f709d24552bacf83f28674feba", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075850+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8d1bbf5df9eb48d6b3733ad85a8996bc", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075893+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ef8418f4aa9f449c94fabf2495e8f165", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2a15c77960741f3ae9ac4828dfa4cd2", "lastModified": "2026-10-21T17:21:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.075978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ffab80fda052481fafa9ebaccc15f20c", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.076021+00:00", "framework": "vllm_fix_tokenizer", "intentId": "712900befa014318baa63fc111a88e4f", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.076063+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6f74e4004ec6485b8c5e61e75d98d8cc", "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": "b7d2aa9701334576ac4e9af70d6fb384", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:16:25.076105+00:00", "framework": "vllm_fix_tokenizer", "intentId": "50f92193a770468d81ce4bec78c8a706", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "971f0ef2a6134def91e59fd7c13b5628", "completedAt": "2026-10-25T04:14:49.535652+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:14:46.981764+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ad526720eb7a43a1a0a45229adf6bbd2", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "971f0ef2a6134def91e59fd7c13b5628", "completedAt": "2026-10-25T04:14:49.535649+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:14:46.981722+00:00", "framework": "vllm_fix_tokenizer", "intentId": "79fd987bee70494da1b67ba8fc93bad2", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "971f0ef2a6134def91e59fd7c13b5628", "completedAt": "2026-10-25T04:14:49.535646+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:14:46.981680+00:00", "framework": "vllm_fix_tokenizer", "intentId": "00895a092f53461481bac99a74c7f782", "repoId": "ukisai/Swift-1.5-5bit-MLX", "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 bf5c943852..17029040a2 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "1c7c5471875164d0ee02685db9ee0d91ff14a64a87227ade4c319c9a296c3067", - ".modelhub_state/architecture_compatibility_blacklist.json": "6eeacffea91850fddaf50c3955949793b6deb54550837a1922829404db50e02d", + ".modelhub_state/architecture_compatibility_blacklist.json": "fd9d946908e9ab62ac140ba35b6e1a8a1e69eea0c6a30844c2e40297ecaa7dec", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "03e25b0691217eee8724bd58866a84b33f284517119cf4ee8781d481008b7884", - ".modelhub_state/official_capabilities.json": "94243db4b0fb52824781921d7d1f82f4fd384f58004099f17c95c944f8b9ab89", - ".modelhub_state/outcome_checkpoint.json": "b60f57e215e66614b9e64f8074f32015d96766989314ee8d606c688171e8c28b", + ".modelhub_state/market_intelligence.json": "e2894663ef5c6e73ace2f16fcdaee30c60ac837a4337b65c9bdc6a028a83a1d7", + ".modelhub_state/official_capabilities.json": "8b2c59f6f481ef9d5d4911e5d0bb29a30bb39cc04b2b8cb52e744e4b2e941610", + ".modelhub_state/outcome_checkpoint.json": "c96d87f9021173c4d3c1214ca218ee53d077f12b8a5b4ff4f405a747f76dbc8e", ".modelhub_state/queue_cleanup_latest.json": "341e6aae8ffd1a8bd62598f03da01e72fbe44f00f20996aa3f865cb969063921", ".modelhub_state/recent_outcomes.jsonl": "70c545e10454f5915994901af1b906a82b12d4e64523c84fdd239767714ac8c4", ".modelhub_state/recovery_active_tasks.jsonl": "af8584c61a1c9eb16e2c9166d3eef5158d691ecdf623581c65c08bace2f453f4", - ".modelhub_state/recovery_intents.jsonl": "0ecdbc3b55b875056aba8bd539b417bab4cba4a820a3369da16ca5be02bc54b4", + ".modelhub_state/recovery_intents.jsonl": "8cfd9a55a0e10584955a3938f46c95fa36a47d4e3bcc1d892995b2dab29f1098", ".modelhub_state/routing_intelligence.json": "22b673184ff76bc899813092860d3c3efc4805a0e4b242327982b4d0b6d2dfa5", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/worker_crashes.jsonl": "e436652d39bca5bcba31822ff9fb949a9d7ff0b7f509c170e258a53d7e01ce9a", "ledger/submissions.jsonl": "148582f3d9ece7ca297d1037d42dae3b40edc3022aab65f6d64f59af8b7672c2", - "outcomes/submissions.jsonl": "387d087b69ce09c4dcf526e7c752dc6a8ace948f60d89ab4fe0f926e45f3b4f4" + "outcomes/submissions.jsonl": "a1c969b5e95f8b548109141b6f48373d90c7e037544ee23241bc066533433345" }, - "generation": 35413, - "phase": "cycle", + "generation": 35414, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-25T04:14:52.403168+00:00", + "updatedAt": "2026-10-25T04:16:25.270361+00:00", "writerId": "5c9906c400e2442789cb0c734d70dc03" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index e65fab0fe3..bcc9c3e6c9 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -313,7 +313,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347633+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "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": "2026-10-06T08:52:25.756975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319955", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347738+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "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": "2026-10-06T08:52:25.752033+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319957", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347964+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.964919+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319967", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347906+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.946650+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319964", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347990+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.047758+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319968", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348121+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "0ff19870d6fc477c61af7cf46bc2f3e6dd4cc9e712cd976a53d87c17d2045bb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.071974+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319969", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347786+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.056438+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319973", "taskType": "text-generation", "verifyResult": null} @@ -1084,8 +1083,8 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T02:42:53.537287+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T18:41:25.446286+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5765199", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:09:41.435018+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-24T20:08:37.639861+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766311", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:09:41.435054+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-24T20:08:37.652020+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766310", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:16:08.741643+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766395", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "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": 14125731418}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:16:08.740412+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766394", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:16:23.645889+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:16:08.741643+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766395", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:16:23.645912+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "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": 14125731418}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:16:08.740412+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766394", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "submitTime": "2026-10-24T20:52:23.183394+00:00", "targetGpu": "MetaX_c-500", "taskId": "5766836", "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": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-24T20:58:11.067331+00:00", "targetGpu": "Biren_166m", "taskId": "5766914", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115836146, "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": 18115836146}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T22:30:40.628995+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5767969", "taskType": "text-generation", "verifyResult": null}