diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index c467c53691..694d7073a5 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -487,7 +487,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-22T18:59:50.263987+00:00", + "generatedAt": "2026-10-22T19:01:31.750127+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 8a294e2f32..fabf39ab12 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-22T18:59:50.357353+00:00", + "generatedAt": "2026-10-22T19:01:31.870111+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 1e9f574aba..371f56dc0f 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-22T18:59:50.357353+00:00", + "catalogUpdatedAt": "2026-10-22T19:01:31.870111+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-22T18:59:50.357353+00:00", + "generatedAt": "2026-10-22T19:01:31.870111+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6578,6 +6578,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-22T18:59:50.357353+00:00", + "taskTreeUpdatedAt": "2026-10-22T19:01:31.870111+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 708c3b0d45..dddfd984d5 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-22T18:37:14.450819+00:00", - "lastSyncTime": "2026-10-22T18:37:12.352873+00:00", + "generatedAt": "2026-10-22T19:01:31.650437+00:00", + "lastSyncTime": "2026-10-22T19:01:31.377014+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1063,29 +1063,29 @@ "unresolvedFailureCount": 11 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation": { - "attributableFailureCount": 33, - "decisionFailureRate": 0.7857, - "decisionSuccessRate": 0.2143, - "decisionTotal": 42, + "attributableFailureCount": 34, + "decisionFailureRate": 0.7907, + "decisionSuccessRate": 0.2093, + "decisionTotal": 43, "failureBreakdown": { "ambiguous_runtime": 55, - "framework_architecture_unsupported": 29, + "framework_architecture_unsupported": 30, "model_load": 4, "platform_infrastructure": 1, "参数/模板问题": 5, "验证失败": 3 }, - "failureCount": 97, - "failureRate": 0.9151, + "failureCount": 98, + "failureRate": 0.9159, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, - "successRate": 0.0849, + "successRate": 0.0841, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 106, + "total": 107, "unresolvedFailureCount": 63 }, "Cambricon_mlu-370-x4|vllm|text-generation": { @@ -3266,27 +3266,27 @@ "unresolvedFailureCount": 58 }, "vllm-mlu": { - "attributableFailureCount": 59, - "decisionFailureRate": 0.7284, - "decisionSuccessRate": 0.2716, - "decisionTotal": 81, + "attributableFailureCount": 60, + "decisionFailureRate": 0.7317, + "decisionSuccessRate": 0.2683, + "decisionTotal": 82, "failureBreakdown": { "ambiguous_runtime": 114, - "framework_architecture_unsupported": 51, + "framework_architecture_unsupported": 52, "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, "参数/模板问题": 47, "验证失败": 3 }, - "failureCount": 224, - "failureRate": 0.9106, + "failureCount": 225, + "failureRate": 0.9109, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0894, - "total": 246, + "successRate": 0.0891, + "total": 247, "unresolvedFailureCount": 164 }, "vllm-patch-tokenizer": { @@ -3390,7 +3390,7 @@ "unresolvedFailureCount": 341 } }, - "generatedAt": "2026-10-22T18:37:14.437488+00:00", + "generatedAt": "2026-10-22T19:01:31.636878+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3479,15 +3479,15 @@ "unresolvedFailureCount": 608 }, "Cambricon_mlu-370-x4": { - "attributableFailureCount": 767, - "decisionFailureRate": 0.912, - "decisionSuccessRate": 0.088, - "decisionTotal": 841, + "attributableFailureCount": 768, + "decisionFailureRate": 0.9121, + "decisionSuccessRate": 0.0879, + "decisionTotal": 842, "failureBreakdown": { "ambiguous_runtime": 520, "architecture_compatibility": 53, "context_length": 48, - "framework_architecture_unsupported": 319, + "framework_architecture_unsupported": 320, "memory_capacity": 219, "model_load": 8, "platform_infrastructure": 16, @@ -3497,14 +3497,14 @@ "日志缺失": 13, "验证失败": 42 }, - "failureCount": 1673, - "failureRate": 0.9576, + "failureCount": 1674, + "failureRate": 0.9577, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, - "successRate": 0.0424, - "total": 1747, + "successRate": 0.0423, + "total": 1748, "unresolvedFailureCount": 890 }, "Cambricon_mlu-370-x8": { @@ -9263,6 +9263,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|modelopt": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "modelType": "gemma4", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "modelopt", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -36623,6 +36646,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|modelopt|34": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "loadSizeLog2Bucket": 34, + "modelType": "gemma4", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "modelopt", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -60842,20 +60889,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17978, - "totalRecords": 18519, + "terminalRecords": 17979, + "totalRecords": 18520, "totals": { - "attributableFailureCount": 6361, + "attributableFailureCount": 6362, "decisionFailureRate": 0.8658, "decisionSuccessRate": 0.1342, - "decisionTotal": 7347, + "decisionTotal": 7348, "failureBreakdown": { "ambiguous_runtime": 4670, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 136, "context_length": 328, - "framework_architecture_unsupported": 2357, + "framework_architecture_unsupported": 2358, "memory_capacity": 1207, "model_load": 577, "platform_infrastructure": 971, @@ -60866,18 +60913,17 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16992, + "failureCount": 16993, "failureRate": 0.9452, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 971, "successCount": 986, "successRate": 0.0548, - "total": 17978, + "total": 17979, "unresolvedFailureCount": 9660 }, "warnings": [ - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", @@ -60890,6 +60936,7 @@ "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "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 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。", @@ -60906,7 +60953,9 @@ "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 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 Kunlunxin_p-800|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 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 Sunrise_pt-200-x1|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 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 Iluvatar_bi-150|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 Iluvatar_mrv-100|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -60931,12 +60980,10 @@ "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。", "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 Mthreads_s4000|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 Iluvatar_bi-150|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 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 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_bi-150|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。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18519, + "summarizedRecords": 18520, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index ede09da5d7..cedc901345 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3724,6 +3724,18 @@ {"batchId": "9189f5c453744760bed1aee56b9287af", "completedAt": "2026-10-22T17:55:09.184717+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-22T17:54:54.518202+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ed3d1b4f3f542dead2090c7f8877ddd", "lastModified": "2026-10-21T17:19:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-22T18:59:58.689136+00:00", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5722887", "taskType": "text-generation"} {"batchId": "9189f5c453744760bed1aee56b9287af", "completedAt": "2026-10-22T17:55:09.184730+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T17:54:54.518409+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7a8400d2c4324158b95b9588d83fae2b", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "reason": null, "reconciledAt": "2026-10-22T18:59:58.691240+00:00", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5722884", "taskType": "text-generation"} {"batchId": "9189f5c453744760bed1aee56b9287af", "completedAt": "2026-10-22T17:55:09.184737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T17:54:54.518512+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2943bc61f2714655a726db5ad1db11f8", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T18:59:58.689140+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5722886", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272078+00:00", "framework": "llamacpp", "intentId": "e9be711db0fa4667a1c4aed07e34325b", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272253+00:00", "framework": "vllm_tokenizer_patch", "intentId": "90d8c6d466c84825a18d6f15d26e3359", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272354+00:00", "framework": "vllm_tokenizer_patch", "intentId": "035c14c3eaa84d30a98068bb3fc29d0e", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272444+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e1f2aa7be7b4858b4852f9af5edb42d", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272532+00:00", "framework": "vllm_tokenizer_patch", "intentId": "462c102f459f4b39b49a15f326245f14", "lastModified": "2026-10-22T13:57:14+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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272622+00:00", "framework": "vllm-mlu", "intentId": "744e3793fa6d4867b9ba57df02a3d6ce", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272714+00:00", "framework": "vllm-mlu", "intentId": "fcd2405e1cb94d1eb0251af8db6e6393", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272802+00:00", "framework": "vllm-mlu", "intentId": "66a0703d5e9041f48f18e3418631b7aa", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272891+00:00", "framework": "vllm-mlu", "intentId": "0eb81de231a348c889f70ea80921b1a0", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.272978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2bee1dda6c7648f7b9d771f7a9d7279b", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-AWQ-4bit", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.273051+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b568e1813c624b2ba7168386cb3a641f", "lastModified": "2026-10-21T16:41:42+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "e5052f94fd57457cbe50b6e2bd66aac9", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T19:01:34.273124+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b118bf85b5434dc28aafa142ea639223", "lastModified": "2026-10-21T17:13:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-4bit", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "2e1f83bf05f949ebacb1904804080685", "completedAt": "2026-10-22T18:59:53.702175+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T18:59:51.111475+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8c13a52d886f49b6a186f4775ef54d21", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "2e1f83bf05f949ebacb1904804080685", "completedAt": "2026-10-22T18:59:53.702171+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T18:59:51.111433+00:00", "framework": "vllm_fix_tokenizer", "intentId": "996a9ec47fa5451c96267b62a2c5c454", "repoId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "2e1f83bf05f949ebacb1904804080685", "completedAt": "2026-10-22T18:59:53.702167+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T18:59:51.111390+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b472ff7da63b435d8293a2466b602e38", "repoId": "cyankiwi/GLM-4.7-Flash-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 48531aa411..c8dcf39e81 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "9d9b17fdc7f07551ec36ed0e92fdb688b67e0688cc1fa6874d5681bd1be55957", - ".modelhub_state/architecture_compatibility_blacklist.json": "26927d1a6b99b674a699105d8054fb606d3102c36b101924e83dd6fcf51e0f15", + ".modelhub_state/architecture_compatibility_blacklist.json": "2fc1f970678914b43ea6c67f07129db8e8869869de74677817a2b000a4517d59", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "2f02101a77f3992e3106d6a2fe8d1575cb290aef6497ea201877bd13c95de240", - ".modelhub_state/official_capabilities.json": "27ee334e9dc35f56117768007a881f1a2d545656f90ab4b18ec2664838e19070", - ".modelhub_state/outcome_checkpoint.json": "561b2291f5a989e9396c0f40bcac36eb001f0315530c98e6103d83093356f0f3", + ".modelhub_state/market_intelligence.json": "a50b9df943ed85ef6679e012ff2b1b28efe03c387aff0b5fc0595d50668ae7df", + ".modelhub_state/official_capabilities.json": "4fe68b83936c84cdb991090fb3bb1fd380220134fa2912b7e4cdfb9c3e3dd533", + ".modelhub_state/outcome_checkpoint.json": "cfea3c5e7c08049b5d2f789dc246333730dc4003caaa50c6c67ef201f1eed9fc", ".modelhub_state/queue_cleanup_latest.json": "8334310d4dead516bef55821a2fcd0ee22b747cd886dc6d77a07cf9c439bb3f9", ".modelhub_state/recent_outcomes.jsonl": "af80b03c1147019d447a3a33c5bbb83a8733c09983c2a9478b8d3b01bb7a779f", ".modelhub_state/recovery_active_tasks.jsonl": "1953e03d4f3a6e31d51533a264c89c129bcc110f7a39e652f33368063e21c92b", - ".modelhub_state/recovery_intents.jsonl": "3867d8a3a81301ccd72d90dcd1acb17565340f5a0472ad8f86bf31bb9a5cbdbb", + ".modelhub_state/recovery_intents.jsonl": "62fe143ae387aaa6da806a6ad2e63562db6f679003859c62f7a7d419c5d4e19a", ".modelhub_state/routing_intelligence.json": "2ed839fc463a78a760f579ad46f676b9c72f004f12fd740b4957a0d32795ead0", ".modelhub_state/submission_exclusions.jsonl": "e2677e09d968a0c44c65d7c030b9c8ea2c9d39dc378ce302c2a309ab54d600d9", ".modelhub_state/worker_crashes.jsonl": "50e3ab320d986c635b0d4cb9b1de107b33f9ab8864ff5aa9ca00e1b4af9f30cc", "ledger/submissions.jsonl": "4fc2858275362b026ea68142f6598e23018be3b6cd7a040c440454ac3a8301ad", - "outcomes/submissions.jsonl": "b02e62f5f6d9a6b4d768e93b0e4e8c35d38be200d6d52dbf2eb3b66a4a27d076" + "outcomes/submissions.jsonl": "1a683909b5abcf64a22b8944e3929514cc7972d9901eecc986ae274924da01aa" }, - "generation": 29877, - "phase": "cycle", + "generation": 29878, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-22T18:59:58.902711+00:00", + "updatedAt": "2026-10-22T19:01:34.435744+00:00", "writerId": "a94e2cbdfb3d4160878859cdc87771b0" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index cf710f7c28..46bdac113e 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -273,7 +273,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-02T04:08:31.346005+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T20:02:02.754254+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5221297", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-02T14:22:44.450309+00:00", "modelId": "juspay/Xor-26B-A4B", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51612008428, "estimatedRequiredGiB": 57.717, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51644378142}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-02T06:04:07.448713+00:00", "targetGpu": "MetaX_c-500", "taskId": "5229271", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-02T14:37:31.047477+00:00", "modelId": "juspay/Xor-26B-A4B", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51612008428, "estimatedRequiredGiB": 57.717, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 51644378142, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51644378142}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-02T06:31:05.051989+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5229590", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-02T14:50:29.854835+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825736695, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825736695}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-02T06:39:17.144379+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5229695", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-04T00:18:23.253390+00:00", "modelId": "bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "20be4844f511319dd6cea1282e23172995d9476d977f5f90b954fe55b819a00b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1077324288, "estimatedRequiredGiB": 30.563, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 27347406407, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:reasoning", "custom_tag:mathematical", "custom_tag:hybrid-reasoning", "custom_tag:adaptive-reasoning", "custom_tag:efficient-reasoning", "custom_tag:reinforcement-learning", "custom_tag:rlvr", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27347406407}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:13:51.649938+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5260075", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-04T00:18:23.253706+00:00", "modelId": "agentionai/Qwen3.8-Flash-Next-MTP-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "2c7c57bb60ad07dbbddc968bef24d09c2171ac104b9f8d288747b0faeaf022cd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4135893376, "estimatedRequiredGiB": 4.622, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4135901039, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:qwen4exp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4135901039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:13:51.545762+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5260070", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-04T00:18:23.253509+00:00", "modelId": "IFM/K2-Horizon-0.9B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "36bf4da571a91856e98c8e2bd7295629e710569a2e0e7cb87061b61578291ec8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1148614016, "estimatedRequiredGiB": 7.146, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6393786288, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1078285824, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:0.9b", "custom_tag:dense", "custom_tag:reasoning", "custom_tag:knowledge-distillation", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6393786288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:13:51.647319+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5260072", "taskType": "text-generation", "verifyResult": null} @@ -1086,7 +1085,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T18:31:58.798617+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "waiting", "submitTime": "2026-10-22T10:30:26.211847+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5715909", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T18:33:48.248274+00:00", "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 9269343620, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8185253888, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9269343620}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T10:33:00.650947+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5715949", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T18:38:54.662162+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 21404443971, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21404443971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T10:37:23.551169+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5716024", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-22T11:00:57.635451+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5716393", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-22T19:01:31.376989+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-22T11:00:57.635451+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5716393", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T11:31:03.230185+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5716785", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "InternScience/Sage-A1.5-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "6a1e6e554e778bcf41fd30fe0869e8c4a396cf7289db86fcce4b236e83d8b8a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37802150112, "estimatedRequiredGiB": 43.253, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 38701689630, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35505251456, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38701689630}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T12:45:02.852710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5717984", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T12:45:02.861295+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5717983", "taskType": "text-generation", "verifyResult": null}