diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 38ec73be72..f6f68ce18b 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -850,7 +850,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-21T14:06:50.871467+00:00", + "generatedAt": "2026-10-21T14:08:46.018694+00:00", "summary": { "activeBlockCount": 41, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index dcb540276f..d6cd057852 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-21T14:02:51.465948+00:00", + "communityAttemptedAt": "2026-10-21T14:08:46.145704+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-21T14:06:50.976328+00:00", + "generatedAt": "2026-10-21T14:08:46.145704+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index de99becadd..9b93a5ca8e 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-21T14:06:50.976328+00:00", + "catalogUpdatedAt": "2026-10-21T14:08:46.145704+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-21T14:06:50.976328+00:00", + "generatedAt": "2026-10-21T14:08:46.145704+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6691,6 +6691,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-21T14:06:50.976328+00:00", + "taskTreeUpdatedAt": "2026-10-21T14:08:46.145704+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 8bf7b6e8b6..6b736b1c11 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-21T13:05:59.426893+00:00", - "lastSyncTime": "2026-10-21T13:05:59.174747+00:00", + "generatedAt": "2026-10-21T14:08:45.915982+00:00", + "lastSyncTime": "2026-10-21T14:08:44.566023+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1436,25 +1436,25 @@ "decisionSuccessRate": 0.2143, "decisionTotal": 42, "failureBreakdown": { - "ambiguous_runtime": 52, + "ambiguous_runtime": 53, "framework_architecture_unsupported": 29, "model_load": 4, "platform_infrastructure": 1, "参数/模板问题": 5, "验证失败": 3 }, - "failureCount": 94, - "failureRate": 0.9126, + "failureCount": 95, + "failureRate": 0.9135, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, - "successRate": 0.0874, + "successRate": 0.0865, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 103, - "unresolvedFailureCount": 60 + "total": 104, + "unresolvedFailureCount": 61 }, "Cambricon_mlu-370-x4|vllm|text-generation": { "attributableFailureCount": 25, @@ -3637,7 +3637,7 @@ "decisionSuccessRate": 0.275, "decisionTotal": 80, "failureBreakdown": { - "ambiguous_runtime": 109, + "ambiguous_runtime": 110, "framework_architecture_unsupported": 50, "model_load": 7, "platform_infrastructure": 1, @@ -3645,15 +3645,15 @@ "参数/模板问题": 47, "验证失败": 3 }, - "failureCount": 218, - "failureRate": 0.9083, + "failureCount": 219, + "failureRate": 0.9087, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0917, - "total": 240, - "unresolvedFailureCount": 159 + "successRate": 0.0913, + "total": 241, + "unresolvedFailureCount": 160 }, "vllm-patch-tokenizer": { "attributableFailureCount": 69, @@ -3756,7 +3756,7 @@ "unresolvedFailureCount": 339 } }, - "generatedAt": "2026-10-21T13:05:59.414024+00:00", + "generatedAt": "2026-10-21T14:08:45.900543+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 132, @@ -3850,7 +3850,7 @@ "decisionSuccessRate": 0.088, "decisionTotal": 841, "failureBreakdown": { - "ambiguous_runtime": 517, + "ambiguous_runtime": 518, "architecture_compatibility": 53, "context_length": 48, "framework_architecture_unsupported": 319, @@ -3863,15 +3863,15 @@ "日志缺失": 13, "验证失败": 42 }, - "failureCount": 1670, + "failureCount": 1671, "failureRate": 0.9576, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, "successRate": 0.0424, - "total": 1744, - "unresolvedFailureCount": 887 + "total": 1745, + "unresolvedFailureCount": 888 }, "Cambricon_mlu-370-x8": { "attributableFailureCount": 71, @@ -9515,6 +9515,29 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|none": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "modelType": "k2_horizon", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -35645,6 +35668,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|none|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "loadSizeLog2Bucket": 34, + "modelType": "k2_horizon", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -59142,15 +59189,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17927, - "totalRecords": 18456, + "terminalRecords": 17928, + "totalRecords": 18457, "totals": { "attributableFailureCount": 6344, "decisionFailureRate": 0.8655, "decisionSuccessRate": 0.1345, "decisionTotal": 7330, "failureBreakdown": { - "ambiguous_runtime": 4653, + "ambiguous_runtime": 4654, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 135, @@ -59166,15 +59213,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16941, + "failureCount": 16942, "failureRate": 0.945, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 971, "successCount": 986, "successRate": 0.055, - "total": 17927, - "unresolvedFailureCount": 9626 + "total": 17928, + "unresolvedFailureCount": 9627 }, "warnings": [ "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", @@ -59237,6 +59284,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18456, + "summarizedRecords": 18457, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index bc96a1e98b..2168f13faf 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3671,6 +3671,18 @@ {"batchId": "0a2e698e3d154068826f68964f7a3306", "completedAt": "2026-10-21T13:05:09.112909+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:05:06.402345+00:00", "framework": "vllm_tokenizer_patch", "intentId": "51e57abb336145669dc86bd20f5c8436", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "reason": null, "reconciledAt": "2026-10-21T14:07:13.035343+00:00", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation"} {"batchId": "8217688bd3674fada06876bba8c42aa3", "completedAt": "2026-10-21T13:16:59.417198+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:16:56.913155+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2cd7f353b95346539c7aa2706b0a5dcf", "lastModified": "2026-10-19T17:23:16+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T14:07:13.032079+00:00", "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5695060", "taskType": "text-generation"} {"batchId": "4b6c1b110509451a837f2a82ede97acd", "completedAt": "2026-10-21T13:18:01.244788+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:17:58.499243+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4126b4b567044a68823ec88f6fef8ca3", "lastModified": "2026-10-19T18:03:45+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T14:07:13.032075+00:00", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5695068", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.523871+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dffc52ba670e4592bd9cbe4f4feab1f4", "lastModified": "2026-10-19T17:09:46+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.523975+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7f3825fd582e4ec3860c0bd330d5728d", "lastModified": "2026-10-21T12:17:17+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B", "repoId": "LiquidAI/LFM2.5-24B-A2B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524024+00:00", "framework": "llamacpp", "intentId": "c43af65cfb364b40bdbfb7d246ce0a07", "lastModified": "2026-10-21T03:15:59+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.6-4B-GGUF", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524087+00:00", "framework": "llamacpp", "intentId": "67ed3a5683c6498b8537c8b62d3e8275", "lastModified": "2026-10-20T13:54:35+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Muse-Glimmer-30B-DFlash2-GGUF", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524145+00:00", "framework": "llamacpp", "intentId": "79d8a6dddbe44394a7642c50104d2409", "lastModified": "2026-10-20T05:58:12+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524210+00:00", "framework": "vllm_tokenizer_patch", "intentId": "03e4bb07eda44f859e112b720fc017af", "lastModified": "2026-10-19T16:59:08+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524264+00:00", "framework": "vllm_tokenizer_patch", "intentId": "102db1a9e7714c4da35f070cb3f0cc4c", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524315+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c3ecadb7d9e4b88915499feb40cbf25", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524364+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9eb680388dfd4ef6b8c035bd7e610c63", "lastModified": "2026-10-19T18:55:19+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-2.1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524413+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6fb6b49a929f4528b1d1d606cea62daa", "lastModified": "2026-10-21T13:30:22+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-14B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-14B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524463+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5a7125f3dec84b4493911ce995217868", "lastModified": "2026-10-21T13:20:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "94d53fa1e6c64bbea4a357b73ddac082", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:08:53.524512+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bf81812b82c4d9f9754d1af12837be6", "lastModified": "2026-10-19T21:32:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Agents-A1-AWQ-NVFP4", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "809460a8412442b3a3550c3dc96b3009", "completedAt": "2026-10-21T14:07:03.144317+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:07:00.484003+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e8cf2f181722454a9c09a86a993a78f6", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "809460a8412442b3a3550c3dc96b3009", "completedAt": "2026-10-21T14:07:03.144313+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:07:00.483955+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3abf0fb073b7431f828e86ad8179b184", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "809460a8412442b3a3550c3dc96b3009", "completedAt": "2026-10-21T14:07:03.144309+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:07:00.483906+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5520479e64134e74a4bf532523110674", "repoId": "cyankiwi/Hermes-4-14B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index b1746dccc7..aa462e4047 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "aeafb438f627623c6464e93fb51f9faf7a4db0c390155d0253fa484ad502e8ca", - ".modelhub_state/architecture_compatibility_blacklist.json": "c164ec1a6662950fd7af36e820d0dc87a4326fb87923874b848f38700c869e02", + ".modelhub_state/architecture_compatibility_blacklist.json": "f76c5e82793548301e0b78264935dbbd3fb707b0f8b59afa74b0e5e7651cdcba", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "a53e42449a75cb3b5285b13b061305e36c8a8400c9734980ddae7b123f8f5bb4", - ".modelhub_state/official_capabilities.json": "c8fd7c83af855c4fdd8586c0afde8b9ae666c60401f66d5ad3c21aef8470e847", - ".modelhub_state/outcome_checkpoint.json": "ae5f3e429953535400649e0e998529a4ca0ceaad7e0b830f13244430d4f13390", + ".modelhub_state/market_intelligence.json": "b90ab11d74c0c65c745072f89af8f3254ddad7e2a68ace020e0f7fbef45500d0", + ".modelhub_state/official_capabilities.json": "ad1ed0b59324fd773cb869161d23254ccdcb3ad448e12384db33a1695f58d71d", + ".modelhub_state/outcome_checkpoint.json": "fdabf4d4d3723d38cd009bc723b164c1e9f0cbdcb545c0fb2936687404f49403", ".modelhub_state/queue_cleanup_latest.json": "f5e4b24f66aee986cd43ef6fdfb7d8debb7011d4b344c791936225a5f5c920ce", ".modelhub_state/recent_outcomes.jsonl": "34964a2369c81d37ca8f7001745b57b669949fff2bd0bf028721300b6868a6b8", ".modelhub_state/recovery_active_tasks.jsonl": "a8b72528f17866e6ac598348a39023f835a33e842aacd9201a806c9d1738503c", - ".modelhub_state/recovery_intents.jsonl": "16dfbd745e87422785d0f69334387a90b34aca188388aa72348b23df4849cff5", + ".modelhub_state/recovery_intents.jsonl": "d5ab7983d294b1030ec93f1a11cf57576476a8a8e0e1e0e4c428b238b69dc076", ".modelhub_state/routing_intelligence.json": "8dd7b6afc92681b9dd33ef3f937957c0031e92adcc94294b08888e0c48d2a371", ".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc", ".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9", "ledger/submissions.jsonl": "359381c462f59640efa5bf9f5826f09489666f3daa0e83b762c15934dd8ffe5c", - "outcomes/submissions.jsonl": "8bc85f54728c97942ec404e631b8c4bd15ce93c55d01d510a5d1ef4524427cdd" + "outcomes/submissions.jsonl": "2de2dcf03d2ad9bf087c23f2710b0d294dab7cbf8e09d026fe1a47c80ceaba8c" }, - "generation": 27047, - "phase": "cycle", + "generation": 27048, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-21T14:07:13.246504+00:00", + "updatedAt": "2026-10-21T14:08:53.695839+00:00", "writerId": "f9d6ac09a4c14ca19fc241d193853c55" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 52c6e6a48c..a443621601 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -162,7 +162,6 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T21:01:22.468510+00:00", "modelId": "z-lab/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "31b0861ad56429ee42697dd4ce872a9717e970d3cf90166c4e6e2fe3b2f5bb19", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561928, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561928}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:00:37.385261+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5019322", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T21:31:27.760080+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2135575312, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:27:47.747400+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5019633", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T22:45:05.970820+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2112106349, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T14:44:16.051430+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5020425", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-23T02:54:50.764789+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.887542+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5023400", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T02:54:50.764828+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754192, "estimatedRequiredGiB": 2.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2057327077}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.889548+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023397", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T03:13:40.768275+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242688, "estimatedRequiredGiB": 2.291, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2049905101, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2049905101}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T19:09:59.407570+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023594", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-23T03:13:40.768267+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920104, "estimatedRequiredGiB": 2.288, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2047574270, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2047574270}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T19:09:59.405343+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5023595", "taskType": "text-generation", "verifyResult": null} @@ -1083,7 +1082,7 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T13:03:09.363160+00:00", "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "a7a7d00616db408ae5c0df2a7cb156b93da7e857ba3eeb80a28825bbcf98f013", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3493762176, "estimatedRequiredGiB": 37.765, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 33791316398, "modelscopeLicense": "mit", "modelscopeParams": 3286633962, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:gguf", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle", "custom_tag:gguf", "custom_tag:ollama", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33791316398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:02:59.629168+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5688914", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T13:03:09.363122+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:02:59.638626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T13:07:51.584082+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:05:58.860026+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688937", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {"architectures": [], "configFingerprint": "5ba0f3d0350c6aad95b8d320dd475d03180877733e000b4e0ec4e7a1a9599db3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229976064, "estimatedRequiredGiB": 4.066, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3638566160, "modelscopeLicense": "apache-2.0", "modelscopeParams": 389223169, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:dspark", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:quantized", "custom_tag:minicpmv", "custom_tag:minicpmv4.7", "custom_tag:text-generation", "custom_tag:vision-understanding", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3638566160}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T06:08:36.740120+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689542", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T14:08:44.565999+00:00", "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {"architectures": [], "configFingerprint": "5ba0f3d0350c6aad95b8d320dd475d03180877733e000b4e0ec4e7a1a9599db3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229976064, "estimatedRequiredGiB": 4.066, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3638566160, "modelscopeLicense": "apache-2.0", "modelscopeParams": 389223169, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:dspark", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:quantized", "custom_tag:minicpmv", "custom_tag:minicpmv4.7", "custom_tag:text-generation", "custom_tag:vision-understanding", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3638566160}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T06:08:36.740120+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689542", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "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": 15859925253, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T06:13:19.034567+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689608", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T06:49:04.032078+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689967", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21000825520, "estimatedRequiredGiB": 23.484, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 21013103805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21013103805}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T07:05:46.531823+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5690178", "taskType": "text-generation", "verifyResult": null}