diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 4faeec3167..c62e715e9f 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-25T18:15:26.732458+00:00", + "generatedAt": "2026-10-25T18:17:13.635906+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 7659b5a05e..7486e7a5ac 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-25T18:15:26.858101+00:00", + "generatedAt": "2026-10-25T18:17:13.755515+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 8d2ed8bb7f..2a8132916c 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-25T18:15:26.858101+00:00", + "catalogUpdatedAt": "2026-10-25T18:17:13.755515+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-25T18:15:26.858101+00:00", + "generatedAt": "2026-10-25T18:17:13.755515+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6903,6 +6903,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-25T18:15:26.858101+00:00", + "taskTreeUpdatedAt": "2026-10-25T18:17:13.755515+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index e121135b79..72d04038f3 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-25T17:20:11.422025+00:00", - "lastSyncTime": "2026-10-25T17:20:11.341504+00:00", + "generatedAt": "2026-10-25T18:17:13.538900+00:00", + "lastSyncTime": "2026-10-25T18:17:13.464675+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -605,20 +605,20 @@ "framework_architecture_unsupported": 46, "memory_capacity": 1, "platform_infrastructure": 1, - "参数/模板问题": 43 + "参数/模板问题": 44 }, - "failureCount": 199, - "failureRate": 0.9803, + "failureCount": 200, + "failureRate": 0.9804, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 4, - "successRate": 0.0197, + "successRate": 0.0196, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 203, - "unresolvedFailureCount": 142 + "total": 204, + "unresolvedFailureCount": 143 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 75, @@ -789,9 +789,9 @@ "framework_architecture_unsupported": 39, "platform_infrastructure": 1, "repository_structure": 1, - "参数/模板问题": 37 + "参数/模板问题": 38 }, - "failureCount": 184, + "failureCount": 185, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -801,8 +801,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 184, - "unresolvedFailureCount": 143 + "total": 185, + "unresolvedFailureCount": 144 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 206, @@ -915,9 +915,9 @@ "failureBreakdown": { "ambiguous_runtime": 161, "memory_capacity": 1, - "参数/模板问题": 11 + "参数/模板问题": 12 }, - "failureCount": 173, + "failureCount": 174, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -927,8 +927,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 173, - "unresolvedFailureCount": 172 + "total": 174, + "unresolvedFailureCount": 173 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 51, @@ -1190,20 +1190,20 @@ "framework_architecture_unsupported": 22, "model_load": 3, "tokenizer_compatibility": 1, - "参数/模板问题": 45 + "参数/模板问题": 46 }, - "failureCount": 133, - "failureRate": 0.911, + "failureCount": 134, + "failureRate": 0.9116, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 13, - "successRate": 0.089, + "successRate": 0.0884, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 146, - "unresolvedFailureCount": 107 + "total": 147, + "unresolvedFailureCount": 108 }, "Cambricon_mlu-370-x8|vllm|text-generation": { "attributableFailureCount": 22, @@ -2079,20 +2079,20 @@ "framework_architecture_unsupported": 38, "model_load": 7, "tokenizer_compatibility": 2, - "参数/模板问题": 28 + "参数/模板问题": 29 }, - "failureCount": 91, - "failureRate": 0.8505, + "failureCount": 92, + "failureRate": 0.8519, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, - "successRate": 0.1495, + "successRate": 0.1481, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", - "total": 107, - "unresolvedFailureCount": 44 + "total": 108, + "unresolvedFailureCount": 45 }, "Kunlunxin_p-800|unknown|text-generation": { "attributableFailureCount": 1, @@ -2348,9 +2348,9 @@ "context_length": 1, "framework_architecture_unsupported": 7, "model_load": 4, - "参数/模板问题": 42 + "参数/模板问题": 43 }, - "failureCount": 58, + "failureCount": 59, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -2360,8 +2360,8 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 58, - "unresolvedFailureCount": 44 + "total": 59, + "unresolvedFailureCount": 45 }, "MetaX_c-500|vllm|feature_emb": { "attributableFailureCount": 1, @@ -2662,20 +2662,20 @@ "memory_capacity": 1, "platform_infrastructure": 36, "tokenizer_compatibility": 100, - "参数/模板问题": 12 + "参数/模板问题": 13 }, - "failureCount": 197, - "failureRate": 0.9899, + "failureCount": 198, + "failureRate": 0.99, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 36, "successCount": 2, - "successRate": 0.0101, + "successRate": 0.01, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 199, - "unresolvedFailureCount": 16 + "total": 200, + "unresolvedFailureCount": 17 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 636, @@ -3039,9 +3039,9 @@ "model_load": 18, "repository_structure": 5, "runtime_memory": 19, - "参数/模板问题": 59 + "参数/模板问题": 60 }, - "failureCount": 183, + "failureCount": 184, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "pendingCount": 0, @@ -3051,8 +3051,8 @@ "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", - "total": 183, - "unresolvedFailureCount": 112 + "total": 184, + "unresolvedFailureCount": 113 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 666, @@ -3225,17 +3225,17 @@ "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 426, - "参数/模板问题": 111 + "参数/模板问题": 112 }, - "failureCount": 6332, + "failureCount": 6333, "failureRate": 0.9828, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 111, "successRate": 0.0172, - "total": 6443, - "unresolvedFailureCount": 1721 + "total": 6444, + "unresolvedFailureCount": 1722 }, "vllm-customized": { "attributableFailureCount": 16, @@ -3271,18 +3271,18 @@ "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, - "参数/模板问题": 55, + "参数/模板问题": 56, "验证失败": 3 }, - "failureCount": 240, - "failureRate": 0.916, + "failureCount": 241, + "failureRate": 0.9163, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.084, - "total": 262, - "unresolvedFailureCount": 176 + "successRate": 0.0837, + "total": 263, + "unresolvedFailureCount": 177 }, "vllm-patch-tokenizer": { "attributableFailureCount": 71, @@ -3295,17 +3295,17 @@ "model_load": 18, "repository_structure": 5, "runtime_memory": 19, - "参数/模板问题": 59 + "参数/模板问题": 60 }, - "failureCount": 183, + "failureCount": 184, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, - "total": 183, - "unresolvedFailureCount": 112 + "total": 184, + "unresolvedFailureCount": 113 }, "vllm_0_17_0_corex_4_4_0": { "attributableFailureCount": 57, @@ -3344,17 +3344,17 @@ "model_load": 13, "platform_infrastructure": 36, "tokenizer_compatibility": 100, - "参数/模板问题": 46 + "参数/模板问题": 48 }, - "failureCount": 725, - "failureRate": 0.9904, + "failureCount": 727, + "failureRate": 0.9905, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 36, "successCount": 7, - "successRate": 0.0096, - "total": 732, - "unresolvedFailureCount": 495 + "successRate": 0.0095, + "total": 734, + "unresolvedFailureCount": 497 }, "vllm_tokenizer_patch": { "attributableFailureCount": 181, @@ -3372,20 +3372,20 @@ "repository_structure": 3, "runtime_memory": 3, "tokenizer_compatibility": 2, - "参数/模板问题": 137 + "参数/模板问题": 140 }, - "failureCount": 542, - "failureRate": 0.9819, + "failureCount": 545, + "failureRate": 0.982, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, - "successRate": 0.0181, - "total": 552, - "unresolvedFailureCount": 358 + "successRate": 0.018, + "total": 555, + "unresolvedFailureCount": 361 } }, - "generatedAt": "2026-10-25T17:20:11.404628+00:00", + "generatedAt": "2026-10-25T18:17:13.522800+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 134, @@ -3401,19 +3401,19 @@ "platform_infrastructure": 1, "repository_structure": 1, "tokenizer_compatibility": 3, - "参数/模板问题": 75, + "参数/模板问题": 76, "日志缺失": 3, "验证失败": 27 }, - "failureCount": 408, - "failureRate": 0.9488, + "failureCount": 409, + "failureRate": 0.949, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0512, - "total": 430, - "unresolvedFailureCount": 273 + "successRate": 0.051, + "total": 431, + "unresolvedFailureCount": 274 }, "Ascend_910-b4": { "attributableFailureCount": 340, @@ -3429,19 +3429,19 @@ "platform_infrastructure": 3, "repository_structure": 28, "tokenizer_compatibility": 11, - "参数/模板问题": 301, + "参数/模板问题": 302, "日志缺失": 14, "验证失败": 175 }, - "failureCount": 1090, - "failureRate": 0.9445, + "failureCount": 1091, + "failureRate": 0.9446, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 64, - "successRate": 0.0555, - "total": 1154, - "unresolvedFailureCount": 747 + "successRate": 0.0554, + "total": 1155, + "unresolvedFailureCount": 748 }, "Biren_166m": { "attributableFailureCount": 194, @@ -3459,19 +3459,19 @@ "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 8, - "参数/模板问题": 226, + "参数/模板问题": 227, "日志缺失": 62, "验证失败": 27 }, - "failureCount": 816, + "failureCount": 817, "failureRate": 0.9703, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0297, - "total": 841, - "unresolvedFailureCount": 620 + "total": 842, + "unresolvedFailureCount": 621 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 771, @@ -3514,18 +3514,18 @@ "model_load": 6, "platform_infrastructure": 2, "tokenizer_compatibility": 3, - "参数/模板问题": 83, + "参数/模板问题": 84, "验证失败": 22 }, - "failureCount": 345, - "failureRate": 0.9583, + "failureCount": 346, + "failureRate": 0.9584, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 15, - "successRate": 0.0417, - "total": 360, - "unresolvedFailureCount": 271 + "successRate": 0.0416, + "total": 361, + "unresolvedFailureCount": 272 }, "Iluvatar_bi-100": { "attributableFailureCount": 194, @@ -3598,19 +3598,19 @@ "repository_structure": 133, "runtime_memory": 1, "tokenizer_compatibility": 118, - "参数/模板问题": 365, + "参数/模板问题": 366, "日志缺失": 6, "验证失败": 47 }, - "failureCount": 1778, + "failureCount": 1779, "failureRate": 0.9095, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, "successRate": 0.0905, - "total": 1955, - "unresolvedFailureCount": 774 + "total": 1956, + "unresolvedFailureCount": 775 }, "Kunlunxin_p-800": { "attributableFailureCount": 99, @@ -3677,19 +3677,19 @@ "repository_structure": 114, "runtime_memory": 2, "tokenizer_compatibility": 79, - "参数/模板问题": 459, + "参数/模板问题": 460, "日志缺失": 15, "验证失败": 48 }, - "failureCount": 1526, - "failureRate": 0.9121, + "failureCount": 1527, + "failureRate": 0.9122, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 147, - "successRate": 0.0879, - "total": 1673, - "unresolvedFailureCount": 831 + "successRate": 0.0878, + "total": 1674, + "unresolvedFailureCount": 832 }, "Mthreads_s4000": { "attributableFailureCount": 97, @@ -3737,18 +3737,18 @@ "repository_structure": 83, "runtime_memory": 1, "tokenizer_compatibility": 285, - "参数/模板问题": 237, + "参数/模板问题": 238, "验证失败": 32 }, - "failureCount": 1495, + "failureCount": 1496, "failureRate": 0.9338, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 260, "successCount": 106, "successRate": 0.0662, - "total": 1601, - "unresolvedFailureCount": 435 + "total": 1602, + "unresolvedFailureCount": 436 }, "Vastai_va16": { "attributableFailureCount": 471, @@ -3795,19 +3795,19 @@ "repository_structure": 121, "runtime_memory": 74, "tokenizer_compatibility": 79, - "参数/模板问题": 443, + "参数/模板问题": 444, "日志缺失": 66, "验证失败": 27 }, - "failureCount": 1647, + "failureCount": 1648, "failureRate": 0.9786, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 4, "successCount": 36, "successRate": 0.0214, - "total": 1683, - "unresolvedFailureCount": 891 + "total": 1684, + "unresolvedFailureCount": 892 } }, "observedGpuMemoryGiB": { @@ -4725,6 +4725,29 @@ "total": 2, "unresolvedFailureCount": 0 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b3", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -6200,6 +6223,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -7812,6 +7858,29 @@ "total": 12, "unresolvedFailureCount": 12 }, + "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 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", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Biren_166m", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -12240,6 +12309,29 @@ "total": 2, "unresolvedFailureCount": 0 }, + "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -16738,6 +16830,29 @@ "total": 7, "unresolvedFailureCount": 1 }, + "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -20275,6 +20390,29 @@ "total": 2, "unresolvedFailureCount": 0 }, + "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "MetaX_c-500", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -22856,6 +22994,29 @@ "total": 3, "unresolvedFailureCount": 0 }, + "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 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", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Sunrise_pt-200-x1", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -25264,6 +25425,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|auto-round": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-patch-tokenizer", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "hygon_k100-ai", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -26486,9 +26670,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 3 + "参数/模板问题": 4 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, @@ -26500,8 +26684,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 0, @@ -26611,12 +26795,12 @@ "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { - "ambiguous_runtime": 2, + "ambiguous_runtime": 1, "framework_architecture_unsupported": 1, "model_load": 4, - "参数/模板问题": 13 + "参数/模板问题": 12 }, - "failureCount": 20, + "failureCount": 18, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastPlatformFailureAt": null, @@ -26628,8 +26812,8 @@ "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", - "total": 20, - "unresolvedFailureCount": 15 + "total": 18, + "unresolvedFailureCount": 13 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 1, @@ -27085,6 +27269,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|auto-round": { + "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-mlu", + "lastTerminalAt": "2026-10-25T18:17:13.464603+00:00", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, @@ -27613,6 +27822,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|auto-round": { + "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", + "lastTerminalAt": "2026-10-25T18:17:13.464647+00:00", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, @@ -28366,6 +28600,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round": { + "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": "2026-10-25T18:17:13.464669+00:00", + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Sunrise_pt-200-x1", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -28517,31 +28776,6 @@ "total": 1, "unresolvedFailureCount": 1 }, - "hygon_k100-ai|vllm-patch-tokenizer|text-generation|plamo3|none": { - "attributableFailureCount": 0, - "consecutiveFailures": 0, - "decisionFailureRate": 0.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 0, - "failureBreakdown": { - "ambiguous_runtime": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm-patch-tokenizer", - "lastTerminalAt": "2026-10-25T06:46:31.238482+00:00", - "modelType": "plamo3", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "hygon_k100-ai", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -30227,6 +30461,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b3", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -32720,6 +32978,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -35313,6 +35595,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 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", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Biren_166m", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -42179,6 +42485,30 @@ "total": 2, "unresolvedFailureCount": 0 }, + "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -48464,6 +48794,30 @@ "total": 3, "unresolvedFailureCount": 1 }, + "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -54043,6 +54397,30 @@ "total": 2, "unresolvedFailureCount": 0 }, + "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "MetaX_c-500", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -57963,6 +58341,30 @@ "total": 2, "unresolvedFailureCount": 0 }, + "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 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", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Sunrise_pt-200-x1", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -61641,6 +62043,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|auto-round|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "参数/模板问题": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-patch-tokenizer", + "loadSizeLog2Bucket": 34, + "modelType": "qwen3_5_text", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "auto-round", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "hygon_k100-ai", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -62673,8 +63099,8 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18085, - "totalRecords": 18629, + "terminalRecords": 18093, + "totalRecords": 18637, "totals": { "attributableFailureCount": 6385, "decisionFailureRate": 0.8662, @@ -62693,35 +63119,35 @@ "repository_structure": 742, "runtime_memory": 101, "tokenizer_compatibility": 700, - "参数/模板问题": 3649, + "参数/模板问题": 3657, "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17099, + "failureCount": 17107, "failureRate": 0.9455, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0545, - "total": 18085, - "unresolvedFailureCount": 9742 + "total": 18093, + "unresolvedFailureCount": 9750 }, "warnings": [ "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 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-x4 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Iluvatar_bi-150|transformers|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。", "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -62768,6 +63194,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18629, + "summarizedRecords": 18637, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 53cf6d2645..035c9940de 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -20,6 +20,7 @@ {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-22T05:17:40.370463+00:00", "modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-14T14:36:16.300431+00:00", "targetGpu": "MetaX_c-500", "taskId": "5536994", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-24T12:21:40.061478+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:37.157740+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520193", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-24T15:31:00.652278+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:36.054072+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520166", "taskType": "text-generation", "verifyResult": null} +{"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T18:17:13.464669+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:35.764285+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520157", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-16T17:41:11.941285+00:00", "modelId": "inclusionAI/Ring-mini-2.0", "modelProfile": {"architectures": ["BailingMoeV2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32513135016, "estimatedRequiredGiB": 36.346, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_moe", "modelscopeFileSize": 32522223867, "modelscopeLicense": "mit", "modelscopeParams": 16255643392, "modelscopeTags": ["license:mit", "model_type:bailing_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 32522223867}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:35.357776+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520150", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-24T08:34:54.442493+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:35.260730+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520147", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-25T07:12:33.440996+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:52:38.762916+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520140", "taskType": "text-generation", "verifyResult": null} @@ -246,6 +247,7 @@ {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255788+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.935477+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321204", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753390+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.934000+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321202", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255746+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.932288+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321205", "taskType": "text-generation", "verifyResult": null} +{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T18:17:13.464603+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.930642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321203", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255854+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.876580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321207", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255724+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.873128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321199", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:39:47.345766+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:56:23.868816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321209", "taskType": "text-generation", "verifyResult": null} @@ -277,6 +279,7 @@ {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560665+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.575997+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321047", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560515+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.573750+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321050", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560553+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.571842+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321045", "taskType": "text-generation", "verifyResult": null} +{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-25T18:17:13.464647+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.570093+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321041", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560576+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.568027+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321039", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T05:42:37.051716+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.564547+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321040", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T12:14:09.655802+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.561317+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321043", "taskType": "text-generation", "verifyResult": null} @@ -295,6 +298,3 @@ {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-10T11:17:52.552115+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.563131+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320870", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-24T12:21:40.061421+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.561419+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320866", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383769+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.559645+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320863", "taskType": "text-generation", "verifyResult": null} -{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-25T06:46:31.238482+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:35:45.554451+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320867", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383953+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.477950+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320861", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383704+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.463228+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320862", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 96b7902597..b319a4601b 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3848,6 +3848,18 @@ {"batchId": "dfcc7d3b56f5432cb796e6c081656d5a", "completedAt": "2026-10-25T16:02:32.089952+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T16:02:29.618576+00:00", "framework": "vllm", "intentId": "e3aa8402c21c4a1ab42a805109958f1b", "lastModified": "2026-10-21T16:25:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T18:15:37.753522+00:00", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "5785631", "taskType": "text-generation"} {"batchId": "657c7d5f77d34704bfebfb34f83b53cc", "completedAt": "2026-10-25T17:23:33.641587+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T17:23:31.377755+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4b92e84de8204f5ea6556d2d8dbe7682", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T18:15:37.752794+00:00", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5786730", "taskType": "text-generation"} {"batchId": "c9f252d16e4d4200ad0c463edd586668", "completedAt": "2026-10-25T18:02:31.047561+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:02:28.648027+00:00", "framework": "vllm-mlu", "intentId": "1c5f77ead5f94dd1b6885f5d4011e6ba", "lastModified": "2026-10-21T15:03:47+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T18:15:37.752792+00:00", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5787259", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559431+00:00", "framework": "vllm-mlu", "intentId": "2adbcc86cf974521a518c7994e92520a", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559537+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f04499480baf4b77ab9a64a1426f7916", "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": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559587+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5703d2db9cf94157af16e09deb306a0c", "lastModified": "2026-10-25T14:40:45+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559630+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c2d95f68f1894fbda9a2ce95f2776924", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559674+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ad5dc1da57334b7891e441653efd9128", "lastModified": "2026-10-21T16:18:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559717+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1acfa4ff17864fc98cb3dddf26843b42", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559759+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d338ad2131ba43fea01ab4e1932cd5dd", "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": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559803+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0b187a39c0b34e95bb810f86647433ef", "lastModified": "2026-10-21T16:25:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-4bit", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559846+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5eb885ab46c147329797cc2f4c1a138c", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559888+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2e44bc7c1cdd498cbfe058a172069780", "lastModified": "2026-10-21T16:38:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559930+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fb2417b660c1415982133c6588176eae", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "aa8d695686fd4c358e1b6baddb04a794", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:17:14.559972+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5419fe8c2e7f4fbbaeac9751d047f69e", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "c35521a282784b89a40a62823a917248", "completedAt": "2026-10-25T18:15:35.786151+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:15:33.291190+00:00", "framework": "vllm_fix_tokenizer", "intentId": "130b96f91bb14506b5ad7efd4b7003cc", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "c35521a282784b89a40a62823a917248", "completedAt": "2026-10-25T18:15:35.786148+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:15:33.291141+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b62c5f8ff85c475293124614c66dd061", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "c35521a282784b89a40a62823a917248", "completedAt": "2026-10-25T18:15:35.786145+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T18:15:33.291099+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d45725dd073740f2922514231c463179", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "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 7f3f337dc2..0f1a4f01f4 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "f67100b6c472c45616d6604638d9ed73402dea8d0c1dd1531185d1caca9e1b58", - ".modelhub_state/architecture_compatibility_blacklist.json": "4e8fe626bd0c0ca80d3cc98a811c55af7383b3ff5e09dab5d4757234f8da488c", + ".modelhub_state/architecture_compatibility_blacklist.json": "c2cb8d262295626c66b9283a6cf8628ccfcd9b86eee8bcab1d2573d0be3b2ab4", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "3e85507e98345d8cb7015d0e1e9d5eec6f8b4eed3016d93d80fbe2f9d0bb3e0f", - ".modelhub_state/official_capabilities.json": "35e4f997414a8c5a1c13e6ae2e8272ac1645ce9d4506459bdab690e0308014b7", - ".modelhub_state/outcome_checkpoint.json": "7ece9a3207ea0ac06ea44e0ecc887e177ab0e66f4c729e2d1d20ee82bc1b7e9f", + ".modelhub_state/market_intelligence.json": "597212bbc40854b3b0b83a811f3c2b12aa9ddd0899385733a934d70604bdc62d", + ".modelhub_state/official_capabilities.json": "62968bbc868a26aea01fd23607cb85ce7cc5c9377a9fdcd0385b1e05a6d79f0c", + ".modelhub_state/outcome_checkpoint.json": "59b94a9bb3feb46de9776e8ba3c78dadec6c3780631431060815d088fef3df07", ".modelhub_state/queue_cleanup_latest.json": "057df969e2051a87bb6c7a4245b3505ac66b790746ad963a8d6637fe89e861de", - ".modelhub_state/recent_outcomes.jsonl": "295d02cdd19aa31a8087903ff97272cbe6bc614847d4ab4126d783ee6e2c1e49", + ".modelhub_state/recent_outcomes.jsonl": "2aaadf840f124a48b66154628ebb14de2eb4bfde12cb304e1aaae01c7dbed8de", ".modelhub_state/recovery_active_tasks.jsonl": "48ae2002ba6f22b11b12f18a2b45fa28f7d4420678fc0f8f4872811922d29d42", - ".modelhub_state/recovery_intents.jsonl": "bed11d2f4724ffd4e97a91a4f1153fc6d60481ed3262d80ca64895ef24c9b9c6", + ".modelhub_state/recovery_intents.jsonl": "7b355201da2af3ef1e41aaeb9107a886129c74ac53fcdd2cc773e6a0ae786730", ".modelhub_state/routing_intelligence.json": "5f79c4c443ece2886c50f8de4178df8b3acd34dd7e818e4ea4785b38e8b4dd9c", ".modelhub_state/submission_exclusions.jsonl": "3db506f4d37bc78a9069d6022969e3718fa3eb1dad129907c99f63d5a7300ba1", ".modelhub_state/worker_crashes.jsonl": "0fc6c3913ba6a3ff00019bfaff56ce222acc4b192a4ed26e7f61a0bec8699b05", "ledger/submissions.jsonl": "8665dd29f35721ee8f978b3672e6c2bf36f49f5cec8826cbbe288affa2ed8399", - "outcomes/submissions.jsonl": "e0bcfd640568fabcdf5548d772b52faec0a7a5c0e8d0321915134b6cc48f79a5" + "outcomes/submissions.jsonl": "98524390bbc8978aa147622f38d27fbba8118d93a98db85bfa7c68bafe005243" }, - "generation": 36874, - "phase": "cycle", + "generation": 36875, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-25T18:15:37.976622+00:00", + "updatedAt": "2026-10-25T18:17:14.738636+00:00", "writerId": "7ff73e6204284f23bc2b88b7c29d21d9" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index a15100f676..3e96d37502 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -165,7 +165,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T03:34:38.852724+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3320832164, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790145}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:31:41.444748+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5046023", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-24T03:34:38.852704+00:00", "modelId": "IFM/K2-Horizon-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a015ad361c8b35c70c85648256a591979967ef38682323a28f85efdfa8060bd0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9573964160, "estimatedRequiredGiB": 59.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 53374659671, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53374659671}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:33:16.585033+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5046043", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T03:51:15.462063+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3320832164, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790145}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:47:42.048287+00:00", "targetGpu": "Vastai_va16", "taskId": "5046271", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T14:06:39.057071+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:05:15.403300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:24:00.455827+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:21:33.668586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054819", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "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": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+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": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null} @@ -264,7 +263,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253503+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "0a1dbeb37891c11a4d439b0dc783c89f1ca6323ea07398122fc1d7f8cfe8d96f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.962708+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260089", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253696+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.954522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260093", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253639+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-03T16:15:49.154928+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260094", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253471+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.161002+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260095", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253604+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.356198+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260103", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253493+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.565606+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260116", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253414+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-03T16:15:49.563992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260111", "taskType": "text-generation", "verifyResult": null} @@ -296,7 +294,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:32:26.862488+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 5045067151, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:05:30.743848+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319429", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:32:26.862464+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 5045067151, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:23:48.552550+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5319658", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347924+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-06T08:50:49.343842+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319928", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347930+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.256812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319929", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348141+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.254703+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319935", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347746+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.554613+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319948", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347912+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.748983+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319954", "taskType": "text-generation", "verifyResult": null} @@ -344,7 +341,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952117+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952898+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-06T09:13:59.669160+00:00", "targetGpu": "Biren_166m", "taskId": "5320458", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952246+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.678748+00:00", "targetGpu": "Biren_166m", "taskId": "5320457", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952888+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.661697+00:00", "targetGpu": "Biren_166m", "taskId": "5320470", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952111+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.748096+00:00", "targetGpu": "Biren_166m", "taskId": "5320472", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952345+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.745687+00:00", "targetGpu": "Biren_166m", "taskId": "5320473", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952681+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.659954+00:00", "targetGpu": "Biren_166m", "taskId": "5320471", "taskType": "text-generation", "verifyResult": null} @@ -385,7 +381,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951965+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.247174+00:00", "targetGpu": "Biren_166m", "taskId": "5320843", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952427+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.167694+00:00", "targetGpu": "Biren_166m", "taskId": "5320845", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952084+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-06T09:34:33.164156+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320847", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952966+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.269594+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320851", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952520+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.328612+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320853", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952640+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.359681+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320860", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953062+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.754698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320874", "taskType": "text-generation", "verifyResult": null} @@ -407,7 +402,6 @@ {"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": "2026-10-06T18:06:36.952500+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "263f4cb5e779de4b0b61f97834829c54e77136bc79bad2edf386dfd62b327794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.647771+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321044", "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": "2026-10-06T18:06:36.952399+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.570093+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321041", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953048+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.654004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321038", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952049+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.660362+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321054", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952941+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.756287+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321052", "taskType": "text-generation", "verifyResult": null} @@ -425,7 +419,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952269+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "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": 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": "2026-10-06T09:47:42.948174+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321086", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952703+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "497ab91cb1ba127d73c571f3ec8297e040a03e575e3c6ce93ccd36aa425663ac", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.928461+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321201", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952378+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-06T09:56:23.951340+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321208", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952477+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.930642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321203", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952471+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.852267+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321216", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951782+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.062922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321220", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952801+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.859242+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321214", "taskType": "text-generation", "verifyResult": null} @@ -802,7 +795,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051680+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:36.273148+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520171", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051648+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-13T21:53:35.768953+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520161", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051811+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.757850+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520160", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051609+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.764285+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520157", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051518+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:36.089159+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520165", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051844+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.768026+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520159", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T05:54:00.051428+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:36.360975+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520175", "taskType": "text-generation", "verifyResult": null} @@ -1085,14 +1077,14 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T15:09:24.343675+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-10-25T07:09:12.869621+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5775023", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-25T15:11:03.242640+00:00", "modelId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021920, "estimatedRequiredGiB": 35.117, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 31422264685, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:coding", "custom_tag:agent", "custom_tag:4b", "custom_tag:compact"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31422264685}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T07:10:06.602050+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5775036", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T17:21:48.758787+00:00", "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5806978504, "estimatedRequiredGiB": 6.496, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 5812546890, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5812546890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T09:20:23.633926+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5776685", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "submitTime": "2026-10-25T10:15:41.136812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5778062", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-25T10:15:41.132398+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5778059", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 7.167, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 6413020232, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "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": 6413020232}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:15:41.140077+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5778063", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064405564, "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": 33064405564}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:15:41.128066+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5778060", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80658248464, "estimatedRequiredGiB": 90.177, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 80688709284, "modelscopeLicense": "other", "modelscopeParams": 123611033088, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3", "custom_tag:latent-moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 80688709284}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:15:41.135756+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5778064", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-10-25T10:15:41.141661+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5778061", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:16:32.330930+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5778093", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Solar-Open-100B-AWQ-4bit", "modelProfile": {"architectures": ["SolarOpenForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 61186182168, "estimatedRequiredGiB": 68.407, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "solar_open", "modelscopeFileSize": 61209233197, "modelscopeLicense": "other", "modelscopeParams": 102651799552, "modelscopeTags": ["license:other", "model_type:solar_open", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:upstage", "custom_tag:solar", "custom_tag:moe", "custom_tag:100b", "custom_tag:llm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 61209233197}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:16:32.338860+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5778092", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T18:17:13.464612+00:00", "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-25T10:15:41.136812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5778062", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T18:17:13.464566+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-25T10:15:41.132398+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5778059", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T18:17:13.464640+00:00", "modelId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 7.167, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 6413020232, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "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": 6413020232}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T10:15:41.140077+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5778063", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T18:17:13.464594+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064405564, "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": 33064405564}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T10:15:41.128066+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5778060", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T18:17:13.464627+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80658248464, "estimatedRequiredGiB": 90.177, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 80688709284, "modelscopeLicense": "other", "modelscopeParams": 123611033088, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3", "custom_tag:latent-moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 80688709284}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T10:15:41.135756+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5778064", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T18:17:13.464661+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T10:15:41.141661+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5778061", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T18:17:13.464545+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T10:16:32.330930+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5778093", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T18:17:13.464655+00:00", "modelId": "cyankiwi/Solar-Open-100B-AWQ-4bit", "modelProfile": {"architectures": ["SolarOpenForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 61186182168, "estimatedRequiredGiB": 68.407, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "solar_open", "modelscopeFileSize": 61209233197, "modelscopeLicense": "other", "modelscopeParams": 102651799552, "modelscopeTags": ["license:other", "model_type:solar_open", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:upstage", "custom_tag:solar", "custom_tag:moe", "custom_tag:100b", "custom_tag:llm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 61209233197}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T10:16:32.338860+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5778092", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "InternScience/Sage-A1.5-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365363088, "estimatedRequiredGiB": 44.025, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 39392487901, "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": "compressed-tensors", "repositoryOnDiskBytes": 39392487901}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T11:04:02.412822+00:00", "targetGpu": "Biren_166m", "taskId": "5779345", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "pending", "submitTime": "2026-10-25T11:39:21.767581+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5780290", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13849505352, "estimatedRequiredGiB": 15.501, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13869693303, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9409813744, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.5", "custom_tag:code", "custom_tag:agent", "custom_tag:sft", "custom_tag:omnicoder", "custom_tag:tesslate"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13869693303}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T11:46:49.387847+00:00", "targetGpu": "Vastai_va16", "taskId": "5780488", "taskType": "text-generation", "verifyResult": null}