diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 0335eb6702..01cfbc6a78 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -567,7 +567,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-26T05:35:51.643200+00:00", + "generatedAt": "2026-10-26T05:37:31.306243+00:00", "summary": { "activeBlockCount": 28, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index a5dd69e60f..b17ee3068f 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-26T05:35:51.776113+00:00", + "generatedAt": "2026-10-26T05:37:31.430034+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 757a36d9f1..26d4ee0d68 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-26T05:35:51.776113+00:00", + "catalogUpdatedAt": "2026-10-26T05:37:31.430034+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-26T05:35:51.776113+00:00", + "generatedAt": "2026-10-26T05:37:31.430034+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6772,6 +6772,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-26T05:35:51.776113+00:00", + "taskTreeUpdatedAt": "2026-10-26T05:37:31.430034+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 47803ffc84..ec73ab4dfe 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-26T05:30:47.088492+00:00", - "lastSyncTime": "2026-10-26T05:30:46.739623+00:00", + "generatedAt": "2026-10-26T05:37:31.195851+00:00", + "lastSyncTime": "2026-10-26T05:37:30.781771+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2767,7 +2767,7 @@ "decisionSuccessRate": 0.0185, "decisionTotal": 648, "failureBreakdown": { - "ambiguous_runtime": 109, + "ambiguous_runtime": 110, "architecture_compatibility": 43, "backend_operator": 33, "context_length": 34, @@ -2779,7 +2779,7 @@ "tokenizer_compatibility": 182, "参数/模板问题": 12 }, - "failureCount": 981, + "failureCount": 982, "failureRate": 0.9879, "framework": "vllm", "pendingCount": 0, @@ -2789,8 +2789,8 @@ "successRate": 0.0121, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 993, - "unresolvedFailureCount": 121 + "total": 994, + "unresolvedFailureCount": 122 }, "Sunrise_pt-200-x1|vllm|unknown": { "attributableFailureCount": 2, @@ -3297,7 +3297,7 @@ "decisionSuccessRate": 0.0292, "decisionTotal": 3838, "failureBreakdown": { - "ambiguous_runtime": 1610, + "ambiguous_runtime": 1611, "architecture_compatibility": 112, "attention_backend": 3, "backend_operator": 98, @@ -3311,15 +3311,15 @@ "tokenizer_compatibility": 426, "参数/模板问题": 116 }, - "failureCount": 6340, + "failureCount": 6341, "failureRate": 0.9826, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 112, "successRate": 0.0174, - "total": 6452, - "unresolvedFailureCount": 1726 + "total": 6453, + "unresolvedFailureCount": 1727 }, "vllm-customized": { "attributableFailureCount": 16, @@ -3469,7 +3469,7 @@ "unresolvedFailureCount": 369 } }, - "generatedAt": "2026-10-26T05:30:47.071831+00:00", + "generatedAt": "2026-10-26T05:37:31.178524+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 136, @@ -3811,7 +3811,7 @@ "decisionSuccessRate": 0.1176, "decisionTotal": 910, "failureBreakdown": { - "ambiguous_runtime": 166, + "ambiguous_runtime": 167, "architecture_compatibility": 44, "backend_operator": 44, "context_length": 39, @@ -3824,15 +3824,15 @@ "参数/模板问题": 240, "验证失败": 32 }, - "failureCount": 1501, + "failureCount": 1502, "failureRate": 0.9335, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 260, "successCount": 107, "successRate": 0.0665, - "total": 1608, - "unresolvedFailureCount": 438 + "total": 1609, + "unresolvedFailureCount": 439 }, "Vastai_va16": { "attributableFailureCount": 471, @@ -23873,6 +23873,29 @@ "total": 3, "unresolvedFailureCount": 0 }, + "Sunrise_pt-200-x1|vllm|text-generation|aquila3|none": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "modelType": "aquila3", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Sunrise_pt-200-x1", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Sunrise_pt-200-x1|vllm|text-generation|cohere2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -60258,6 +60281,30 @@ "total": 2, "unresolvedFailureCount": 0 }, + "Sunrise_pt-200-x1|vllm|text-generation|aquila3|none|12": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "loadSizeLog2Bucket": 12, + "modelType": "aquila3", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Sunrise_pt-200-x1", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Sunrise_pt-200-x1|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -64754,15 +64801,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18142, - "totalRecords": 18686, + "terminalRecords": 18143, + "totalRecords": 18687, "totals": { "attributableFailureCount": 6397, "decisionFailureRate": 0.8663, "decisionSuccessRate": 0.1337, "decisionTotal": 7384, "failureBreakdown": { - "ambiguous_runtime": 4712, + "ambiguous_runtime": 4713, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, @@ -64778,15 +64825,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17155, + "failureCount": 17156, "failureRate": 0.9456, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 987, "successRate": 0.0544, - "total": 18142, - "unresolvedFailureCount": 9786 + "total": 18143, + "unresolvedFailureCount": 9787 }, "warnings": [ "GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。", @@ -64838,17 +64885,17 @@ "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": 18686, + "summarizedRecords": 18687, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index c3e60542ac..991e2f1a34 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3910,6 +3910,18 @@ {"batchId": "fe98bbe446c14af8a16cdb62a7b98b31", "completedAt": "2026-10-26T04:18:05.784406+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:18:03.639774+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c247cd656eae4a09b91a60ea09c880db", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T05:35:59.354455+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795832", "taskType": "text-generation"} {"batchId": "fe98bbe446c14af8a16cdb62a7b98b31", "completedAt": "2026-10-26T04:18:05.784423+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:18:03.639988+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b3037b062d56438fae3946cac4f3ff6c", "lastModified": "2026-10-21T18:55:40+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-bf16", "reason": null, "reconciledAt": "2026-10-26T05:35:59.357718+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-bf16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795834", "taskType": "text-generation"} {"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": "2026-10-26T05:35:59.351664+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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738596+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8bc2c1e9ba104abe8a8b7abb1237f07b", "lastModified": "2026-10-21T15:40:39+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738717+00:00", "framework": "vllm_fix_tokenizer", "intentId": "71f522bb1aa64f86b7d8f5d5e48537e5", "lastModified": "2026-10-25T13:17:58+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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738766+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4cfa0d2964344329b9d33d91d563dffa", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738811+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e236923703a4499997ea3808df6b760", "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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738854+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d39028211ea24c7e8f59c5b3faa67450", "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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738898+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31ac11bb68e144119242df53da5c65f4", "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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738942+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c02cede201d14490b8618c2be2c9ed31", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.738987+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fa81957c8c2e4e3a970988485c138171", "lastModified": "2026-10-21T16:12:30+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Thinking-2507-AWQ-8bit", "repoId": "cyankiwi/Qwen3-4B-Thinking-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.739030+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc1ada3fd7d9415da66370b390957dc5", "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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.739073+00:00", "framework": "vllm_fix_tokenizer", "intentId": "90dd198c7898416e90dd14cc8ab5e9c0", "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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.739117+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d6fb521755504788842aa98313ac1d4c", "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": "c8c3c46621fc4238b49572cf2b961328", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:37:34.739160+00:00", "framework": "vllm_fix_tokenizer", "intentId": "98c0bef0de8742d6bdcb6cd8c02e3b1e", "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": "568b9f819dc945078dc32958931d748a", "completedAt": "2026-10-26T05:35:57.260482+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:35:54.706236+00:00", "framework": "vllm_fix_tokenizer", "intentId": "95b7ad9293b6420ab8d5561705a0fa15", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "568b9f819dc945078dc32958931d748a", "completedAt": "2026-10-26T05:35:57.260479+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:35:54.706187+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d679ef48687242fb9d927e1c5b2f1a62", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "568b9f819dc945078dc32958931d748a", "completedAt": "2026-10-26T05:35:57.260476+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T05:35:54.706134+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b2ff39ea01a54ad8a31d132d61737648", "repoId": "cyankiwi/Olmo-3.1-32B-Think-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 1ef9e7c220..3a71a39250 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "bee734c890ba57e856bc81de3c626c210325f965a736c116328140dc17469b7d", - ".modelhub_state/architecture_compatibility_blacklist.json": "a21c7f2f908f0b7861f23179f06cbf1ddad442f94f9c652d54633f7b891303c8", + ".modelhub_state/architecture_compatibility_blacklist.json": "6c76938814bd1244b76892848eead9a935037de9034000d615b1bf07aae22f9f", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "48014eef75a0ad2ca1827f09b0cf89dadf1f2ed76076d28842dd56f358b4a49e", - ".modelhub_state/official_capabilities.json": "d436231b9fa58339dd861da7be9a2c4b61026db790cb4b79701c514b11d3edc4", - ".modelhub_state/outcome_checkpoint.json": "6e67d023c27e43f9e2e59d3e493b2567b64e97ca815c2fd0055fbf181070d56a", + ".modelhub_state/market_intelligence.json": "cb651f2028357062a12f73d5f62e0194f3efbe779bb5d11cbd0005d5ec564588", + ".modelhub_state/official_capabilities.json": "83d803801b3d898539954e3d3dbc29858c31b22de8c736ea6147595b5ea6de56", + ".modelhub_state/outcome_checkpoint.json": "a8381b98b318aae3847f123a98c1e62decf824ffb96e3adea02ba0be7037873a", ".modelhub_state/queue_cleanup_latest.json": "7bd72ff2e667a4a298c39a875e1fcc18df3107c26d7a8c8cdef8d8f8dabf2611", ".modelhub_state/recent_outcomes.jsonl": "bb6f4ee6ba6da47a0697c3cf5fb9019c4d60b699f04694e45972407d89bd0363", ".modelhub_state/recovery_active_tasks.jsonl": "59dde381f5140f7ec5c9a3229d1a7e02244b02a671dbb2c6189c3b49cb25b2e3", - ".modelhub_state/recovery_intents.jsonl": "65a11b0b8eec6818d9e0bc802dfb157dbcf7afd61698449d36d68e1e56d9e87b", + ".modelhub_state/recovery_intents.jsonl": "b06403e9c19c067c583e51fc15fd0373710a0d34336eb77d26256ddb13bb0cee", ".modelhub_state/routing_intelligence.json": "87fe003bfcd532772e7e304f52f135f6deabc4641174cd00373e6b6a6af5647f", ".modelhub_state/submission_exclusions.jsonl": "bec721d27d733285faddfa9c457d1882988a145ee87f4fbf285ac5deb38326c9", ".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9", "ledger/submissions.jsonl": "4499d1e0f10f75b2308c7fb4824c2fb1fe7ed81b29d97adf7b0d49bda29e1786", - "outcomes/submissions.jsonl": "41a80f7c5b0f25af4ee2a8affd8593327aff5078369677355bb90e2fae18e30b" + "outcomes/submissions.jsonl": "9d122205d2629929d29914d93f7a151b5e793ec5c463f0ad8994fa5c30b09e0a" }, - "generation": 37964, - "phase": "cycle", + "generation": 37965, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-26T05:35:59.599953+00:00", + "updatedAt": "2026-10-26T05:37:34.927531+00:00", "writerId": "dffce16061d848e398e5b5b22f649ccc" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 3159194c4d..2ec22b3545 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -108,7 +108,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T08:17:25.672470+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:03:59.684853+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990026", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T08:25:31.485626+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.964, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16073634582, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16073634582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:22:06.134784+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990307", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295624+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:19:31.687350+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876320+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:55:59.084023+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4995631", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876368+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:57:36.079435+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4995632", "taskType": "text-generation", "verifyResult": null} @@ -1087,7 +1086,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:06:12.366376+00:00", "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432701212, "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", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5432701212}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:05:33.562829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790179", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T05:25:42.758447+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-25T21:24:09.627969+00:00", "targetGpu": "Vastai_va16", "taskId": "5790451", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:30:46.739598+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35211965376, "estimatedRequiredGiB": 39.364, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 35221904676, "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": 35221904676}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T21:30:27.259204+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5790519", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "pending", "submitTime": "2026-10-25T21:36:50.963076+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5790605", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-26T05:37:30.781744+00:00", "modelId": "IFM/Jais-3-3.7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-10-25T21:36:50.963076+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5790605", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "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": "pending", "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": null, "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": "pending", "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": null, "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": "pending", "submitTime": "2026-10-25T22:42:41.230032+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5791447", "taskType": "text-generation", "verifyResult": null}