diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index fda6e224a5..94b5ea17a9 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -588,7 +588,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-26T06:45:33.151511+00:00", + "generatedAt": "2026-10-26T06:47:28.191153+00:00", "summary": { "activeBlockCount": 29, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 0695184cb6..d0932afcbe 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-26T06:45:33.272029+00:00", + "generatedAt": "2026-10-26T06:47:28.265127+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index a6a5a40686..a2de0b0685 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-26T06:45:33.272029+00:00", + "catalogUpdatedAt": "2026-10-26T06:47:28.265127+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-26T06:45:48.464754+00:00", + "generatedAt": "2026-10-26T06:47:28.265127+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6493,6 +6493,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-26T06:45:33.272029+00:00", + "taskTreeUpdatedAt": "2026-10-26T06:47:28.265127+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index ba1171fd4c..aafcda8dff 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-26T06:42:15.418598+00:00", - "lastSyncTime": "2026-10-26T06:42:12.635847+00:00", + "generatedAt": "2026-10-26T06:47:28.069586+00:00", + "lastSyncTime": "2026-10-26T06:47:25.348929+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2175,28 +2175,28 @@ "unresolvedFailureCount": 57 }, "Iluvatar_mrv-100|vllm|text-generation": { - "attributableFailureCount": 50, - "decisionFailureRate": 0.7576, - "decisionSuccessRate": 0.2424, - "decisionTotal": 66, + "attributableFailureCount": 51, + "decisionFailureRate": 0.7612, + "decisionSuccessRate": 0.2388, + "decisionTotal": 67, "failureBreakdown": { "ambiguous_runtime": 16, "framework_architecture_unsupported": 40, "model_load": 8, - "tokenizer_compatibility": 2, + "tokenizer_compatibility": 3, "参数/模板问题": 31 }, - "failureCount": 97, - "failureRate": 0.8584, + "failureCount": 98, + "failureRate": 0.8596, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, - "successRate": 0.1416, + "successRate": 0.1404, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", - "total": 113, + "total": 114, "unresolvedFailureCount": 47 }, "Kunlunxin_p-800|unknown|text-generation": { @@ -3313,10 +3313,10 @@ "unresolvedFailureCount": 6559 }, "vllm": { - "attributableFailureCount": 3729, + "attributableFailureCount": 3730, "decisionFailureRate": 0.9708, "decisionSuccessRate": 0.0292, - "decisionTotal": 3841, + "decisionTotal": 3842, "failureBreakdown": { "ambiguous_runtime": 1611, "architecture_compatibility": 112, @@ -3329,17 +3329,17 @@ "platform_infrastructure": 888, "repository_structure": 470, "runtime_memory": 66, - "tokenizer_compatibility": 427, + "tokenizer_compatibility": 428, "参数/模板问题": 116 }, - "failureCount": 6344, + "failureCount": 6345, "failureRate": 0.9827, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 112, "successRate": 0.0173, - "total": 6456, + "total": 6457, "unresolvedFailureCount": 1727 }, "vllm-customized": { @@ -3490,7 +3490,7 @@ "unresolvedFailureCount": 369 } }, - "generatedAt": "2026-10-26T06:42:15.400864+00:00", + "generatedAt": "2026-10-26T06:47:28.051519+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 136, @@ -3687,10 +3687,10 @@ "unresolvedFailureCount": 1208 }, "Iluvatar_mrv-100": { - "attributableFailureCount": 1000, - "decisionFailureRate": 0.8496, - "decisionSuccessRate": 0.1504, - "decisionTotal": 1177, + "attributableFailureCount": 1001, + "decisionFailureRate": 0.8497, + "decisionSuccessRate": 0.1503, + "decisionTotal": 1178, "failureBreakdown": { "ambiguous_runtime": 356, "architecture_compatibility": 47, @@ -3702,19 +3702,19 @@ "platform_infrastructure": 7, "repository_structure": 133, "runtime_memory": 1, - "tokenizer_compatibility": 118, + "tokenizer_compatibility": 119, "参数/模板问题": 368, "日志缺失": 6, "验证失败": 47 }, - "failureCount": 1784, - "failureRate": 0.9097, + "failureCount": 1785, + "failureRate": 0.9098, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, - "successRate": 0.0903, - "total": 1961, + "successRate": 0.0902, + "total": 1962, "unresolvedFailureCount": 777 }, "Kunlunxin_p-800": { @@ -16782,6 +16782,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|text-generation|bananaall|none": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "tokenizer_compatibility": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_mrv-100|vllm|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -49674,6 +49697,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|text-generation|bananaall|none|12": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "tokenizer_compatibility": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "loadSizeLog2Bucket": 12, + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_mrv-100|vllm|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -65016,13 +65063,13 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18147, - "totalRecords": 18691, + "terminalRecords": 18148, + "totalRecords": 18692, "totals": { - "attributableFailureCount": 6400, + "attributableFailureCount": 6401, "decisionFailureRate": 0.8664, "decisionSuccessRate": 0.1336, - "decisionTotal": 7387, + "decisionTotal": 7388, "failureBreakdown": { "ambiguous_runtime": 4713, "architecture_compatibility": 212, @@ -65035,19 +65082,19 @@ "platform_infrastructure": 973, "repository_structure": 742, "runtime_memory": 101, - "tokenizer_compatibility": 704, + "tokenizer_compatibility": 705, "参数/模板问题": 3679, "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17160, + "failureCount": 17161, "failureRate": 0.9456, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 973, "successCount": 987, "successRate": 0.0544, - "total": 18147, + "total": 18148, "unresolvedFailureCount": 9787 }, "warnings": [ @@ -65100,17 +65147,17 @@ "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|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 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "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 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18691, + "summarizedRecords": 18692, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index c2f6c2bd61..d599847df6 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3912,6 +3912,18 @@ {"batchId": "c6c7b47e653540aa9ff30c6db5212b63", "completedAt": "2026-10-26T04:19:03.775975+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:19:01.480725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc0e62c204e742fa9a40633ce402167c", "lastModified": "2026-10-21T15:51:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-26T06:45:53.896633+00:00", "repoId": "cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795848", "taskType": "text-generation"} {"batchId": "601fe9b0e0584b0d8d9e8d5cc699e2dd", "completedAt": "2026-10-26T06:29:23.876573+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:29:10.468369+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a5792fd3717b4089aecd94b60813310d", "lastModified": "2026-10-25T13:17:58+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "reason": null, "reconciledAt": "2026-10-26T06:45:53.896279+00:00", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5797185", "taskType": "text-generation"} {"batchId": "601fe9b0e0584b0d8d9e8d5cc699e2dd", "completedAt": "2026-10-26T06:29:23.876582+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:29:10.468500+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1bf00e3cb52a4c54b899264b4d852f00", "lastModified": "2026-10-20T14:21:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "reason": null, "reconciledAt": "2026-10-26T06:45:53.896275+00:00", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5797186", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336435+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e060fe67add84f8abef8783ed4ea3e97", "lastModified": "2026-10-25T18:35:45+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nanbeige4.3-33B-FP8", "repoId": "primitive-ai/Nanbeige4.3-33B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336550+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0b92659c7f044d9ab95642d9291866c2", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336602+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b18352f12f634408a04cb0db0a333676", "lastModified": "2026-10-21T17:04:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336647+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3b1cc015b7a647b383c40146a5f489ff", "lastModified": "2026-10-25T13:57:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336696+00:00", "framework": "vllm_fix_tokenizer", "intentId": "70bc6983eb1545508f43a1255e72b13d", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336768+00:00", "framework": "vllm_fix_tokenizer", "intentId": "063f989542f6456aafcec6d889d5d6c8", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336824+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bbebd5263fb1410cafad24e3e4cd885a", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336889+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d4eebd7321ab4ffbb5f24ddbc3d297fd", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336935+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7c8eae386e234574bbb3e8827a425e9e", "lastModified": "2026-10-21T17:00:21+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2-8B-A1B-AWQ-4bit", "repoId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.336979+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0a3cae2b880347b9a68336a31d0e8f9e", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.337023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "23e7f96222c44c27aa8d84835b7065ff", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "6b31f09832b54821bbfdfa48199eb665", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:47:32.337067+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c7cd8905514442f9a66ca6e9bb468928", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "d7b5e35a029f475a8befff9729ce9503", "completedAt": "2026-10-26T06:45:51.899334+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:45:49.314246+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bb5e8b3f88e44afd90c3e5ad5a4254b7", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "d7b5e35a029f475a8befff9729ce9503", "completedAt": "2026-10-26T06:45:51.899332+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:45:49.314203+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5fdca36721b54411b164d7bbbb765f4c", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "d7b5e35a029f475a8befff9729ce9503", "completedAt": "2026-10-26T06:45:51.899329+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:45:49.314153+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0467b03642094cee817ca249879f1bd2", "repoId": "cyankiwi/KAT-Dev-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 7f35ea0013..aa676be178 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "460e046e5b96997d719bad65de824a18e626cbd6e4fd47e376e8a31accabb30c", - ".modelhub_state/architecture_compatibility_blacklist.json": "735b6300e63d97b5377b704ddf80c6037b3ccbc3ea62cc8a5bf26cbd9466c0bf", + ".modelhub_state/architecture_compatibility_blacklist.json": "a2bf042c1273743217e92ab59d4f46d7c97d29a460d7862ca5305ed248ac4ee3", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "cce0c30d37bfdbdfbf71e21e0cfff63fef13603df801b3be5adb6e11b78aa650", - ".modelhub_state/official_capabilities.json": "43b45b44848196cb955134dc2832aff30c672a11ca15f03ad4584e1e54305bc4", - ".modelhub_state/outcome_checkpoint.json": "1760fa79cfc06533205f958e6eb4f7c0181ffeed76764c4f3dcdbb4e8159b479", + ".modelhub_state/market_intelligence.json": "46d3e25100a4618f3293fe681309bea55cbc1f84d6cc087460ad6658a0cf4741", + ".modelhub_state/official_capabilities.json": "a33661588fdd47902e1b680d6d2882743ddb65468530785c80de8af2c8b4fe45", + ".modelhub_state/outcome_checkpoint.json": "92dc4f45659a3cb83f887eee2dcfbb32b557681f5bdd4eb649aed514d09c5d47", ".modelhub_state/queue_cleanup_latest.json": "697c9d3694b85a56b121ba68a978a51c8e9e302e28ae675245e74f1dbccfaaf7", ".modelhub_state/recent_outcomes.jsonl": "a6c12727c0303752d88e9787e25d07d78523fd740088ebaa0a5d0c21e79138c6", ".modelhub_state/recovery_active_tasks.jsonl": "db2c695d054ef821edb46c5aaae6f13a26cbc4e1d072f6f40317a46bda769028", - ".modelhub_state/recovery_intents.jsonl": "44afa002b6c902b16a29c3232f7f70b81e93bed6ce60d1b6ccbff946ec3ae83c", + ".modelhub_state/recovery_intents.jsonl": "09f0287bfd76911d8971ba676b202692f95395fde3c5717f0299be9e32c9427c", ".modelhub_state/routing_intelligence.json": "7cdf6b81794171e33d9c769c52aa3cd4f9c26adc2aead09101d972c072a6e7fb", ".modelhub_state/submission_exclusions.jsonl": "bec721d27d733285faddfa9c457d1882988a145ee87f4fbf285ac5deb38326c9", ".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9", "ledger/submissions.jsonl": "938741a134e47ba3b9241e8ec62e91fe69ed9fa0532de6b83ecf174755b43174", - "outcomes/submissions.jsonl": "2a527f462fb4b14629c8e486f9fd9ddc44d9cc77c491886e303e5a975a099cb7" + "outcomes/submissions.jsonl": "ead8c5dba3deb22fea588d20df3519d30dc765647b5f602d43c9bb06d1ff54fa" }, - "generation": 38084, - "phase": "cycle", + "generation": 38085, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-26T06:45:54.149915+00:00", + "updatedAt": "2026-10-26T06:47:32.525027+00:00", "writerId": "dffce16061d848e398e5b5b22f649ccc" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 26cee93ed3..c7ad253e27 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -368,7 +368,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952623+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.380008+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320890", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953053+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.458983+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320894", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952834+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.457520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320895", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951819+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-06T09:46:35.565915+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321046", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952389+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-06T09:47:42.075531+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321064", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952714+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-06T09:47:42.150650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321070", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952155+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-06T09:47:42.149448+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321072", "taskType": "text-generation", "verifyResult": null} @@ -1086,7 +1085,7 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T06:05:48.058920+00:00", "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["IQuestLoopCoderForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23517027912, "estimatedRequiredGiB": 26.285, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "iquestloopcoder", "modelscopeFileSize": 23519230439, "modelscopeLicense": "other", "modelscopeParams": 39794696320, "modelscopeTags": ["license:other", "model_type:iquestloopcoder", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23519230439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T22:04:35.425298+00:00", "targetGpu": "Vastai_va16", "taskId": "5790962", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T06:05:48.058944+00:00", "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6342166448, "estimatedRequiredGiB": 7.112, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6363495404, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:3.7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6363495404}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T22:04:35.429168+00:00", "targetGpu": "Vastai_va16", "taskId": "5790963", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T06:43:54.053483+00:00", "modelId": "IFM/Jais-3-32B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37350407624, "estimatedRequiredGiB": 41.766, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 37371953913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779304960, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:32B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2, "参数/模板问题": 2}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-24T18:37:46.581678+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 37371953913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T22:42:41.230032+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5791447", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619096698, "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": 19619096698}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T22:46:50.134327+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5791492", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T06:47:25.348904+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619096698, "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": 19619096698}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T22:46:50.134327+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5791492", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T22:49:30.246870+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5791537", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "InternScience/Sage-A1.5", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71908137648, "estimatedRequiredGiB": 80.39, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71931809917, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 71931809917}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T22:51:59.661249+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5791562", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115830100, "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": 18115830100}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T23:11:07.438406+00:00", "targetGpu": "Vastai_va16", "taskId": "5791777", "taskType": "text-generation", "verifyResult": null}