diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index c96ac8ff54..799cb8733b 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-25T07:10:56.640057+00:00", + "generatedAt": "2026-10-25T07:12:33.617367+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 959056b978..42ecaa49ea 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-25T07:10:56.757168+00:00", + "generatedAt": "2026-10-25T07:12:33.735494+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index d4df9afe57..2236221ae1 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-25T07:10:56.757168+00:00", + "catalogUpdatedAt": "2026-10-25T07:12:33.735494+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-25T07:10:56.757168+00:00", + "generatedAt": "2026-10-25T07:12:33.735494+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6718,6 +6718,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-25T07:10:56.757168+00:00", + "taskTreeUpdatedAt": "2026-10-25T07:12:33.735494+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 85b67cd468..5373af7506 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-25T06:46:31.513753+00:00", - "lastSyncTime": "2026-10-25T06:46:31.238482+00:00", + "generatedAt": "2026-10-25T07:12:33.508436+00:00", + "lastSyncTime": "2026-10-25T07:12:33.441018+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -605,20 +605,20 @@ "framework_architecture_unsupported": 45, "memory_capacity": 1, "platform_infrastructure": 1, - "参数/模板问题": 42 + "参数/模板问题": 43 }, - "failureCount": 197, - "failureRate": 0.9801, + "failureCount": 198, + "failureRate": 0.9802, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 4, - "successRate": 0.0199, + "successRate": 0.0198, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 201, - "unresolvedFailureCount": 141 + "total": 202, + "unresolvedFailureCount": 142 }, "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": 36 + "参数/模板问题": 37 }, - "failureCount": 181, + "failureCount": 182, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -801,8 +801,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 181, - "unresolvedFailureCount": 140 + "total": 182, + "unresolvedFailureCount": 141 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 206, @@ -915,9 +915,9 @@ "failureBreakdown": { "ambiguous_runtime": 158, "memory_capacity": 1, - "参数/模板问题": 10 + "参数/模板问题": 11 }, - "failureCount": 169, + "failureCount": 170, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -927,8 +927,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 169, - "unresolvedFailureCount": 168 + "total": 170, + "unresolvedFailureCount": 169 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 51, @@ -1066,21 +1066,21 @@ "framework_architecture_unsupported": 33, "model_load": 4, "platform_infrastructure": 1, - "参数/模板问题": 9, + "参数/模板问题": 10, "验证失败": 3 }, - "failureCount": 105, - "failureRate": 0.9211, + "failureCount": 106, + "failureRate": 0.9217, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, - "successRate": 0.0789, + "successRate": 0.0783, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 114, - "unresolvedFailureCount": 67 + "total": 115, + "unresolvedFailureCount": 68 }, "Cambricon_mlu-370-x4|vllm|text-generation": { "attributableFailureCount": 25, @@ -1758,20 +1758,20 @@ "memory_capacity": 1, "model_load": 8, "runtime_memory": 10, - "参数/模板问题": 27 + "参数/模板问题": 28 }, - "failureCount": 121, - "failureRate": 0.8643, + "failureCount": 122, + "failureRate": 0.8652, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1357, + "successRate": 0.1348, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 140, - "unresolvedFailureCount": 65 + "total": 141, + "unresolvedFailureCount": 66 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 9, @@ -2147,9 +2147,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 201, - "参数/模板问题": 14 + "参数/模板问题": 15 }, - "failureCount": 215, + "failureCount": 216, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -2159,8 +2159,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 215, - "unresolvedFailureCount": 215 + "total": 216, + "unresolvedFailureCount": 216 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 61, @@ -2274,22 +2274,22 @@ "context_length": 13, "memory_capacity": 1, "repository_structure": 14, - "参数/模板问题": 362, + "参数/模板问题": 363, "日志缺失": 1, "验证失败": 48 }, - "failureCount": 542, - "failureRate": 0.8237, + "failureCount": 543, + "failureRate": 0.824, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 116, - "successRate": 0.1763, + "successRate": 0.176, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 658, - "unresolvedFailureCount": 514 + "total": 659, + "unresolvedFailureCount": 515 }, "MetaX_c-500|unknown|unknown": { "attributableFailureCount": 0, @@ -2692,9 +2692,9 @@ "repository_structure": 75, "runtime_memory": 1, "tokenizer_compatibility": 182, - "参数/模板问题": 11 + "参数/模板问题": 12 }, - "failureCount": 980, + "failureCount": 981, "failureRate": 0.9889, "framework": "vllm", "pendingCount": 0, @@ -2704,8 +2704,8 @@ "successRate": 0.0111, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 991, - "unresolvedFailureCount": 120 + "total": 992, + "unresolvedFailureCount": 121 }, "Sunrise_pt-200-x1|vllm|unknown": { "attributableFailureCount": 2, @@ -3192,19 +3192,19 @@ "repository_structure": 264, "runtime_memory": 3, "tokenizer_compatibility": 158, - "参数/模板问题": 3198, + "参数/模板问题": 3199, "日志缺失": 719, "验证失败": 673 }, - "failureCount": 8460, + "failureCount": 8461, "failureRate": 0.9122, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 42, "successCount": 814, "successRate": 0.0878, - "total": 9274, - "unresolvedFailureCount": 6558 + "total": 9275, + "unresolvedFailureCount": 6559 }, "vllm": { "attributableFailureCount": 3720, @@ -3224,17 +3224,17 @@ "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 425, - "参数/模板问题": 109 + "参数/模板问题": 110 }, - "failureCount": 6327, + "failureCount": 6328, "failureRate": 0.9828, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 111, "successRate": 0.0172, - "total": 6438, - "unresolvedFailureCount": 1719 + "total": 6439, + "unresolvedFailureCount": 1720 }, "vllm-customized": { "attributableFailureCount": 16, @@ -3270,18 +3270,18 @@ "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, - "参数/模板问题": 54, + "参数/模板问题": 55, "验证失败": 3 }, - "failureCount": 238, - "failureRate": 0.9154, + "failureCount": 239, + "failureRate": 0.9157, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0846, - "total": 260, - "unresolvedFailureCount": 174 + "successRate": 0.0843, + "total": 261, + "unresolvedFailureCount": 175 }, "vllm-patch-tokenizer": { "attributableFailureCount": 71, @@ -3318,17 +3318,17 @@ "memory_capacity": 1, "model_load": 8, "runtime_memory": 10, - "参数/模板问题": 27 + "参数/模板问题": 28 }, - "failureCount": 121, - "failureRate": 0.8643, + "failureCount": 122, + "failureRate": 0.8652, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1357, - "total": 140, - "unresolvedFailureCount": 65 + "successRate": 0.1348, + "total": 141, + "unresolvedFailureCount": 66 }, "vllm_fix_tokenizer": { "attributableFailureCount": 194, @@ -3343,17 +3343,17 @@ "model_load": 13, "platform_infrastructure": 36, "tokenizer_compatibility": 100, - "参数/模板问题": 43 + "参数/模板问题": 45 }, - "failureCount": 717, - "failureRate": 0.9903, + "failureCount": 719, + "failureRate": 0.9904, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 36, "successCount": 7, - "successRate": 0.0097, - "total": 724, - "unresolvedFailureCount": 487 + "successRate": 0.0096, + "total": 726, + "unresolvedFailureCount": 489 }, "vllm_tokenizer_patch": { "attributableFailureCount": 179, @@ -3371,20 +3371,20 @@ "repository_structure": 3, "runtime_memory": 3, "tokenizer_compatibility": 2, - "参数/模板问题": 135 + "参数/模板问题": 137 }, - "failureCount": 535, + "failureCount": 537, "failureRate": 0.9817, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, "successRate": 0.0183, - "total": 545, - "unresolvedFailureCount": 353 + "total": 547, + "unresolvedFailureCount": 355 } }, - "generatedAt": "2026-10-25T06:46:31.498496+00:00", + "generatedAt": "2026-10-25T07:12:33.493687+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3400,19 +3400,19 @@ "platform_infrastructure": 1, "repository_structure": 1, "tokenizer_compatibility": 3, - "参数/模板问题": 74, + "参数/模板问题": 75, "日志缺失": 3, "验证失败": 27 }, - "failureCount": 406, - "failureRate": 0.9486, + "failureCount": 407, + "failureRate": 0.9487, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0514, - "total": 428, - "unresolvedFailureCount": 272 + "successRate": 0.0513, + "total": 429, + "unresolvedFailureCount": 273 }, "Ascend_910-b4": { "attributableFailureCount": 340, @@ -3428,19 +3428,19 @@ "platform_infrastructure": 3, "repository_structure": 28, "tokenizer_compatibility": 11, - "参数/模板问题": 300, + "参数/模板问题": 301, "日志缺失": 14, "验证失败": 175 }, - "failureCount": 1087, + "failureCount": 1088, "failureRate": 0.9444, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 64, "successRate": 0.0556, - "total": 1151, - "unresolvedFailureCount": 744 + "total": 1152, + "unresolvedFailureCount": 745 }, "Biren_166m": { "attributableFailureCount": 194, @@ -3458,19 +3458,19 @@ "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 8, - "参数/模板问题": 224, + "参数/模板问题": 225, "日志缺失": 62, "验证失败": 27 }, - "failureCount": 811, + "failureCount": 812, "failureRate": 0.9701, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0299, - "total": 836, - "unresolvedFailureCount": 615 + "total": 837, + "unresolvedFailureCount": 616 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 771, @@ -3487,19 +3487,19 @@ "platform_infrastructure": 16, "repository_structure": 85, "tokenizer_compatibility": 35, - "参数/模板问题": 319, + "参数/模板问题": 320, "日志缺失": 13, "验证失败": 42 }, - "failureCount": 1681, - "failureRate": 0.9578, + "failureCount": 1682, + "failureRate": 0.9579, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, - "successRate": 0.0422, - "total": 1755, - "unresolvedFailureCount": 894 + "successRate": 0.0421, + "total": 1756, + "unresolvedFailureCount": 895 }, "Cambricon_mlu-370-x8": { "attributableFailureCount": 72, @@ -3566,19 +3566,19 @@ "repository_structure": 99, "runtime_memory": 13, "tokenizer_compatibility": 60, - "参数/模板问题": 349, + "参数/模板问题": 350, "日志缺失": 155, "验证失败": 30 }, - "failureCount": 2000, - "failureRate": 0.9302, + "failureCount": 2001, + "failureRate": 0.9303, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 150, - "successRate": 0.0698, - "total": 2150, - "unresolvedFailureCount": 1206 + "successRate": 0.0697, + "total": 2151, + "unresolvedFailureCount": 1207 }, "Iluvatar_mrv-100": { "attributableFailureCount": 996, @@ -3626,19 +3626,19 @@ "repository_structure": 2, "runtime_memory": 3, "tokenizer_compatibility": 1, - "参数/模板问题": 58, + "参数/模板问题": 59, "日志缺失": 1, "验证失败": 23 }, - "failureCount": 472, + "failureCount": 473, "failureRate": 0.9854, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 7, "successRate": 0.0146, - "total": 479, - "unresolvedFailureCount": 372 + "total": 480, + "unresolvedFailureCount": 373 }, "Kunlunxin_r-200-8f": { "attributableFailureCount": 0, @@ -3676,19 +3676,19 @@ "repository_structure": 114, "runtime_memory": 2, "tokenizer_compatibility": 79, - "参数/模板问题": 458, + "参数/模板问题": 459, "日志缺失": 15, "验证失败": 48 }, - "failureCount": 1523, + "failureCount": 1524, "failureRate": 0.912, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 147, "successRate": 0.088, - "total": 1670, - "unresolvedFailureCount": 829 + "total": 1671, + "unresolvedFailureCount": 830 }, "Mthreads_s4000": { "attributableFailureCount": 95, @@ -3736,18 +3736,18 @@ "repository_structure": 83, "runtime_memory": 1, "tokenizer_compatibility": 285, - "参数/模板问题": 236, + "参数/模板问题": 237, "验证失败": 32 }, - "failureCount": 1494, - "failureRate": 0.9337, + "failureCount": 1495, + "failureRate": 0.9338, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 260, "successCount": 106, - "successRate": 0.0663, - "total": 1600, - "unresolvedFailureCount": 434 + "successRate": 0.0662, + "total": 1601, + "unresolvedFailureCount": 435 }, "Vastai_va16": { "attributableFailureCount": 471, @@ -4823,9 +4823,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { - "framework_architecture_unsupported": 6 + "framework_architecture_unsupported": 6, + "参数/模板问题": 1 }, - "failureCount": 6, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", @@ -4837,8 +4838,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 6, - "unresolvedFailureCount": 0 + "total": 7, + "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, @@ -6273,9 +6274,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { - "framework_architecture_unsupported": 4 + "framework_architecture_unsupported": 4, + "参数/模板问题": 1 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", @@ -6287,8 +6289,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 0 + "total": 5, + "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, @@ -7909,9 +7911,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 19, - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 21, + "failureCount": 22, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", @@ -7923,8 +7925,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 21, - "unresolvedFailureCount": 21 + "total": 22, + "unresolvedFailureCount": 22 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, @@ -9982,10 +9984,10 @@ "decisionTotal": 10, "failureBreakdown": { "framework_architecture_unsupported": 10, - "参数/模板问题": 2, + "参数/模板问题": 3, "验证失败": 1 }, - "failureCount": 13, + "failureCount": 14, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", @@ -9997,8 +9999,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 13, - "unresolvedFailureCount": 3 + "total": 14, + "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, @@ -14803,9 +14805,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10, - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 12, + "failureCount": 13, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", @@ -14817,8 +14819,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 12, - "unresolvedFailureCount": 12 + "total": 13, + "unresolvedFailureCount": 13 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, @@ -18198,9 +18200,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 22, - "参数/模板问题": 3 + "参数/模板问题": 4 }, - "failureCount": 25, + "failureCount": 26, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", @@ -18212,8 +18214,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 25, - "unresolvedFailureCount": 25 + "total": 26, + "unresolvedFailureCount": 26 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none": { "attributableFailureCount": 0, @@ -23342,9 +23344,9 @@ "failureBreakdown": { "framework_architecture_unsupported": 9, "platform_infrastructure": 8, - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 19, + "failureCount": 20, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", @@ -23356,8 +23358,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 19, - "unresolvedFailureCount": 2 + "total": 20, + "unresolvedFailureCount": 3 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, @@ -25922,9 +25924,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -25936,8 +25938,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 4, @@ -25973,9 +25975,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -25987,8 +25989,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|unknown|text-generation": { "attributableFailureCount": 0, @@ -26259,13 +26261,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 11 + "参数/模板问题": 12 }, - "failureCount": 11, + "failureCount": 12, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-10-22T05:17:40.370515+00:00", + "lastTerminalAt": "2026-10-25T07:12:33.440912+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -26273,8 +26275,8 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 11, - "unresolvedFailureCount": 11 + "total": 12, + "unresolvedFailureCount": 12 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 2, @@ -26415,9 +26417,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, @@ -26429,8 +26431,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Vastai_va16|unknown|text-generation": { "attributableFailureCount": 0, @@ -26563,6 +26565,31 @@ } }, "recentProfileCombinationStats": { + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": { + "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_tokenizer_patch", + "lastTerminalAt": "2026-10-25T07:12:33.440966+00:00", + "modelType": "qwen3_5", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "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|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -26613,6 +26640,31 @@ "total": 4, "unresolvedFailureCount": 0 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": { + "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_tokenizer_patch", + "lastTerminalAt": "2026-10-25T07:12:33.441018+00:00", + "modelType": "qwen3_5", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "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|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -27173,9 +27225,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-21T12:36:20.265435+00:00", @@ -27188,8 +27240,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, @@ -28176,9 +28228,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-24T08:34:54.442493+00:00", @@ -28191,8 +28243,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, @@ -28295,31 +28347,6 @@ "total": 1, "unresolvedFailureCount": 0 }, - "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|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": "2026-10-09T23:01:31.562549+00:00", - "modelType": "lfm2", - "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|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -30205,9 +30232,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "framework_architecture_unsupported": 1 + "framework_architecture_unsupported": 1, + "参数/模板问题": 1 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, @@ -30220,8 +30248,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 + "total": 2, + "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": { "attributableFailureCount": 4, @@ -32648,9 +32676,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "framework_architecture_unsupported": 1 + "framework_architecture_unsupported": 1, + "参数/模板问题": 1 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, @@ -32663,8 +32692,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 + "total": 2, + "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": { "attributableFailureCount": 2, @@ -35289,9 +35318,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 6 + "ambiguous_runtime": 6, + "参数/模板问题": 1 }, - "failureCount": 6, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, @@ -35304,8 +35334,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 6, - "unresolvedFailureCount": 6 + "total": 7, + "unresolvedFailureCount": 7 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, @@ -38380,9 +38410,10 @@ "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5, + "参数/模板问题": 1, "验证失败": 1 }, - "failureCount": 6, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, @@ -38395,8 +38426,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 6, - "unresolvedFailureCount": 1 + "total": 7, + "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|34": { "attributableFailureCount": 3, @@ -45557,9 +45588,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 6 + "ambiguous_runtime": 6, + "参数/模板问题": 1 }, - "failureCount": 6, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, @@ -45572,8 +45604,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 6, - "unresolvedFailureCount": 6 + "total": 7, + "unresolvedFailureCount": 7 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, @@ -50600,9 +50632,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 9 + "ambiguous_runtime": 9, + "参数/模板问题": 1 }, - "failureCount": 9, + "failureCount": 10, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, @@ -50615,8 +50648,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 9, - "unresolvedFailureCount": 9 + "total": 10, + "unresolvedFailureCount": 10 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, @@ -58434,9 +58467,10 @@ "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, - "platform_infrastructure": 4 + "platform_infrastructure": 4, + "参数/模板问题": 1 }, - "failureCount": 7, + "failureCount": 8, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, @@ -58449,8 +58483,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 7, - "unresolvedFailureCount": 0 + "total": 8, + "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 5, @@ -62298,8 +62332,8 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18060, - "totalRecords": 18604, + "terminalRecords": 18068, + "totalRecords": 18612, "totals": { "attributableFailureCount": 6379, "decisionFailureRate": 0.8661, @@ -62318,35 +62352,35 @@ "repository_structure": 742, "runtime_memory": 101, "tokenizer_compatibility": 699, - "参数/模板问题": 3639, + "参数/模板问题": 3647, "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17074, + "failureCount": 17082, "failureRate": 0.9454, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0546, - "total": 18060, - "unresolvedFailureCount": 9723 + "total": 18068, + "unresolvedFailureCount": 9731 }, "warnings": [ "GPU Mthreads_s4000 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 Cambricon_mlu-370-x8 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 Vastai_va16 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 Biren_166m 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-100 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 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 hygon_k100-ai 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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -62393,6 +62427,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18604, + "summarizedRecords": 18612, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 5018cc53b9..83e6be0da4 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -1,4 +1,6 @@ +{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-25T07:12:33.440912+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-25T07:11:36+00:00", "targetGpu": "MetaX_c-500", "taskId": "5669006", "taskType": "text-generation", "verifyResult": null} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T04:12:56.440372+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "failed", "status": "success", "submitTime": "2026-10-24T10:37:32.836646+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5758987", "taskType": "text-generation", "verifyResult": -1} +{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T07:12:33.440966+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": 15859917848, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859917848}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-24T04:23:11.562135+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5753394", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-23T14:45:02.363525+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-23T14:44:16+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5373903", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-23T14:45:02.363489+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-23T14:44:15+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321057", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-22T17:13:40.774233+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-22T16:50:25+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5321498", "taskType": "text-generation", "verifyResult": null} @@ -9,6 +11,7 @@ {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-10-21T21:16:24.481139+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-21T21:15:43+00:00", "targetGpu": "MetaX_c-500", "taskId": "5684052", "taskType": "text-generation", "verifyResult": -1} {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T15:19:19.077489+00:00", "modelId": "cyankiwi/Seed-OSS-36B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39901408344, "estimatedRequiredGiB": 44.607, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 39913687201, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39913687201}, "outcome": "failed", "status": "success", "submitTime": "2026-10-21T20:17:01.338621+00:00", "targetGpu": "MetaX_c-500", "taskId": "5701026", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T11:48:09.066588+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "failed", "status": "success", "submitTime": "2026-10-21T16:45:57.061933+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5698067", "taskType": "text-generation", "verifyResult": -1} +{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T07:12:33.441018+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-21T06:13:19.034567+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689608", "taskType": "text-generation", "verifyResult": null} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-10-19T02:18:02.861795+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-19T02:17:42+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332393", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-18T23:11:19.047759+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T23:07:42+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4376891", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-18T20:30:33.153730+00:00", "modelId": "ornith-ai/Ornith-1.0-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T20:15:43+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4353479", "taskType": "text-generation", "verifyResult": -1} @@ -19,6 +22,7 @@ {"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": "2026-10-16T17:41:11.941285+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} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-20T12:39:15.571332+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "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:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:52:38.758920+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520133", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-13T22:17:18.970452+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T13:12:18.147765+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5513114", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-13T22:17:18.970462+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T12:52:58.552750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5512698", "taskType": "text-generation", "verifyResult": null} @@ -184,6 +188,7 @@ {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557134+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.949218+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353400", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557107+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.932770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353396", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-20T12:39:15.571353+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "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:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.931650+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353403", "taskType": "text-generation", "verifyResult": null} +{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-25T07:12:33.440981+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": 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": "2026-10-07T11:46:58.870068+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353399", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753289+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T06:35:26.381282+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349734", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-24T18:37:46.581618+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "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": 8145035684}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T06:35:26.373231+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349735", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753315+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T06:35:26.357823+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349733", "taskType": "text-generation", "verifyResult": null} @@ -293,8 +298,3 @@ {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-24T15:31:00.652225+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-10-06T09:35:45.363114+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320859", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164588+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.361277+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320858", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164526+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.273637+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320854", "taskType": "text-generation", "verifyResult": null} -{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-09T23:01:31.562549+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:35:45.272338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320856", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-10T11:17:52.552103+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.264608+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320855", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383803+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.263007+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320852", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383946+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.260498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320849", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383712+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.258284+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320850", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 64b33e813c..7dc6e99505 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3817,6 +3817,18 @@ {"batchId": "6d3bdabe2a5249f9bc3db33c70ac9281", "completedAt": "2026-10-25T06:27:11.237731+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T06:26:57.304528+00:00", "framework": "vllm-mlu", "intentId": "25e75a2e8d2449a1b86e96cf1248cdfb", "lastModified": "2026-10-21T14:42:38+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T07:11:02.051931+00:00", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5774395", "taskType": "text-generation"} {"batchId": "ff056303094b4a07ba9c1b95c7767bc3", "completedAt": "2026-10-25T07:09:14.318969+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:09:11.995775+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dfacf96cec434d80b4771ba4de1b691f", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "reason": null, "reconciledAt": "2026-10-25T07:11:02.049120+00:00", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5775023", "taskType": "text-generation"} {"batchId": "cb0e55bdd9604b6ea99538d87123023c", "completedAt": "2026-10-25T07:10:07.955116+00:00", "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:10:05.704943+00:00", "framework": "llamacpp", "intentId": "3cf6f6c0af08480aa0cbea9efb57f7c4", "lastModified": "2026-10-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "reason": null, "reconciledAt": "2026-10-25T07:11:02.049105+00:00", "repoId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5775036", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472358+00:00", "framework": "vllm_fix_tokenizer", "intentId": "eeef1e4578bf4b31999a14af6bcc81d1", "lastModified": "2026-10-21T19:51:23+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472471+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1fff782787534f5093f2898f15b3561e", "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": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472519+00:00", "framework": "vllm_fix_tokenizer", "intentId": "385bd673293b4da38d47a6d1073d9ed3", "lastModified": "2026-10-22T14:13:07+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5", "repoId": "InternScience/Sage-A1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472562+00:00", "framework": "vllm_fix_tokenizer", "intentId": "13e0344c15e9405490098764e7ce9711", "lastModified": "2026-10-21T15:39:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-8bit", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472605+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c3df2c1f891f4b24b17935e6285fb46e", "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": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472648+00:00", "framework": "vllm_fix_tokenizer", "intentId": "687985742f01470ca5ede635a187d451", "lastModified": "2026-10-21T16:25:01+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472691+00:00", "framework": "vllm_fix_tokenizer", "intentId": "de814e219dda4b338401df2d59c16052", "lastModified": "2026-10-21T19:49:11+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472734+00:00", "framework": "vllm_fix_tokenizer", "intentId": "704c4c0cb65f44e989328f1faaa18095", "lastModified": "2026-10-21T15:59:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472776+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a8cd17e5ea854a87b5c2a7e139208bce", "lastModified": "2026-10-21T16:02:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472819+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7b2342ca445d4bb68385e202aae26f39", "lastModified": "2026-10-21T17:04:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472863+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f140600e444947498a6a76b984207d8b", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "a73f7c425c154f4dac43bec01dc2699d", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:12:40.472905+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5fd587e85a1449a9815771e2c90f4593", "lastModified": "2026-10-21T17:21:32+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Solar-Open-100B-AWQ-4bit", "repoId": "cyankiwi/Solar-Open-100B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "a2108764db4c4359b6ef6ddf904c27d4", "completedAt": "2026-10-25T07:10:59.950230+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:10:57.561665+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4ff38dfe9e0a4707ae1dece289b410a9", "repoId": "cyankiwi/Solar-Open-100B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "a2108764db4c4359b6ef6ddf904c27d4", "completedAt": "2026-10-25T07:10:59.950227+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:10:57.561623+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fa0f7b57abee4ce88c8289c8c3d6ed65", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "a2108764db4c4359b6ef6ddf904c27d4", "completedAt": "2026-10-25T07:10:59.950224+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T07:10:57.561579+00:00", "framework": "vllm_fix_tokenizer", "intentId": "59be53c857bb4ab590723e493867a90e", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 2c7ec5d6fd..96bf215ea2 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "afea502b22bd97e20074e491ff6e5445138f50506b4caa14572cc3505efbcc73", - ".modelhub_state/architecture_compatibility_blacklist.json": "db61088eaac0a1b3d2a7d2c3dcf2478e8dcaf4661021e4a91ac3673d36f51e51", + ".modelhub_state/architecture_compatibility_blacklist.json": "40f635e9deecfa44836af1bfdcda51cb4788e0b33a1b5846c69b0078df47e076", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "5c7d10817b53071229492a69638aa603f0d17303c239802926f343b88579caa3", - ".modelhub_state/official_capabilities.json": "9ac76e59a92618f503484e6c114b0e23466ed0cf46389bfc52bf6516616f1b31", - ".modelhub_state/outcome_checkpoint.json": "d618a75fdce3e8f040b2b16abb5363d51f75ce9eeabb9941c81b50c550a91772", + ".modelhub_state/market_intelligence.json": "36128117b1871e45c07a5ba26d2edf365df0f92608fe76e3d0861d94b486f47d", + ".modelhub_state/official_capabilities.json": "811aab7479ad6a0254032e46be0d0ad726fe88162c59e049e6245338229e0260", + ".modelhub_state/outcome_checkpoint.json": "3dfbe38dc5c4c663d98303aa6b97d1d2aa29a664edf7d1f91863937f700059f8", ".modelhub_state/queue_cleanup_latest.json": "20ebd311b877efb9036b6e82b9a40e214eba88d0b16553ef9bf4db2c20060c48", - ".modelhub_state/recent_outcomes.jsonl": "b92ed46b450b3ce786c42f5ee0f19d8d0d90ff9849fe13dee2a7e4143e614cc4", + ".modelhub_state/recent_outcomes.jsonl": "f2bf55e84fb382c2a4e1519919c32a8f629ce9fc550e070348dcf4f980b9e43d", ".modelhub_state/recovery_active_tasks.jsonl": "2d9a156e0a15f0ba91af2161b4f2bebdd2bb9396e884cfd30cf9c3fa65c186b2", - ".modelhub_state/recovery_intents.jsonl": "150fabcedc04ab4edcd19e76a2c71321c52bbc668f42cf68f7c75aa14f7e2637", + ".modelhub_state/recovery_intents.jsonl": "9dc68b0a5d05a86930d5e2833f92dcfb0f5daea04f042b0d70fbf7ba654cb45e", ".modelhub_state/routing_intelligence.json": "bb00b77c6a0f013b738aa9b6c5f99fca2b4d36be5e8c435411101b903dc457a5", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/worker_crashes.jsonl": "3527d86c4fe5a43e8c0b1158e6f24e748474fce5a149c696caf4a1da895ac64a", "ledger/submissions.jsonl": "23ffcc14e88cc38b1025d60b1fd771c64c7faa57f5c91f22c2ca4953d24316c1", - "outcomes/submissions.jsonl": "153cdbf8b51a15f84ac6212d5456698936f7705457ce337c7f7880632919f213" + "outcomes/submissions.jsonl": "3f7ce812889a1416d2c2305412c989c272e139f3edfe63568c2e12af43c0939b" }, - "generation": 35730, - "phase": "cycle", + "generation": 35731, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-25T07:11:02.290056+00:00", + "updatedAt": "2026-10-25T07:12:40.634644+00:00", "writerId": "750e06ff79b245419d079bcf827fbb45" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index fb6d55534c..c2b39beee9 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -183,7 +183,6 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-25T05:49:45.553175+00:00", "modelId": "IFM/K2-Horizon-3.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "d32d4df138a14ef6e14ffb9e219187acad60a2bb30d58a67f09cc2c2ddbb1d0e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5386404224, "estimatedRequiredGiB": 33.587, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 30053117770, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30053117770}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T21:48:31.945848+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5069243", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-25T21:25:34.853191+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606194709, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T13:22:40.451978+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5082880", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-25T21:41:44.957732+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606194709, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T13:39:00.656366+00:00", "targetGpu": "Vastai_va16", "taskId": "5083063", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-25T22:32:53.648889+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.726, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15860970658, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15860970658}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T14:26:41.549250+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5083667", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-25T23:52:08.960036+00:00", "modelId": "dealignai/MiniMax-M2.7-JANG_2L-CRACK", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 67220573536, "estimatedRequiredGiB": 75.144, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 67237895067, "modelscopeLicense": "other", "modelscopeParams": 18616144384, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jang", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:apple-silicon", "custom_tag:mlx", "custom_tag:moe", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:crack", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 67237895067}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T15:48:43.946604+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5084850", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-26T02:40:55.456270+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T18:35:31.853448+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5087122", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T02:40:55.456257+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T18:35:31.862248+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5087121", "taskType": "text-generation", "verifyResult": null} @@ -191,7 +190,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T03:01:41.464536+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T18:56:43.360898+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5087340", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-26T04:45:00.143065+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T20:40:46.452338+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5088555", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-26T04:45:00.143073+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T20:40:46.448085+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5088554", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-26T04:45:00.143041+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859852885, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859852885}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-25T20:40:46.446794+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5088553", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-26T19:33:09.154587+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "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": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-26T11:27:31.250241+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5099581", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T19:44:55.260687+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "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": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-26T11:43:40.248293+00:00", "targetGpu": "Vastai_va16", "taskId": "5099879", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T20:48:15.561783+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310889023, "modelscopeLicense": "other", "modelscopeParams": 5321729392, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310895273}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-26T12:47:09.108765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5100778", "taskType": "text-generation", "verifyResult": null} @@ -352,7 +350,6 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953120+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "70fc30548c2dc36d2dafb257d0a9af9499f0b4ee78e93bb3669e56774e585794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3892651456, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "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:granite-4.2", "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:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953001+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cb5d151b2dc44f0b470d106dee740b8a04dd01ff392c2d2ce69e974ff0e2c0fb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.952007+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952893+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953125+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "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": 2201523288, "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": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "verifyResult": null} {"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} @@ -498,7 +495,6 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-07T20:23:14.668383+00:00", "modelId": "agentionai/Qwen3.8-Flash-Next-MTP-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "fd4700e54c874f68d276f01aa0f2a43fe97b95babd7dac8332895341059b06f1", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4135893408, "estimatedRequiredGiB": 4.622, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4135901266, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:qwen4exp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4135901266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:58.828958+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353402", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-07T20:23:14.668258+00:00", "modelId": "wesjos/Mimo-Qwen3.5-9B-Cold-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "d284810aa76d28087fa20c515c03278f422a9923f3f81203e131236440057fcd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9527497856, "estimatedRequiredGiB": 10.648, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9527503039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:", "task:text-generation", "custom_tag:dpo", "custom_tag:lima", "custom_tag:preference-optimization", "custom_tag:style-tuning", "custom_tag:qwen3.5", "custom_tag:llama-cpp", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9527503039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:58.929732+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353398", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-07T20:23:14.668405+00:00", "modelId": "DevQuasar/openbmb.MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c9a8a756cc2fd1f7b385ce8f87b9c1fbd51eb521ef5bd3b5bd97fbfc9fe2d042", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712704, "estimatedRequiredGiB": 11.68, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10450678027, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10450678027}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:58.930167+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353397", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668239+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": 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": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:58.870068+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353399", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668233+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "05dc104fca8c61e0b7e14c3355cdda1d22c2b6dca6c7d2ae77046a8789aa91d4", "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": "2026-10-07T11:46:59.077598+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353404", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668400+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": "2026-10-07T11:46:58.861235+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353401", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668372+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-07T11:46:58.869031+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353407", "taskType": "text-generation", "verifyResult": null} @@ -795,7 +791,6 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-14T04:05:54.875256+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19493321709, "estimatedRequiredGiB": 21.806, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 19511331991, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19511331991}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T20:01:58.663421+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5518622", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T04:05:54.875280+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25484884997, "estimatedRequiredGiB": 28.502, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 25502895279, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25502895279}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T20:01:58.646474+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5518621", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T04:32:55.241111+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19493321709, "estimatedRequiredGiB": 21.806, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 19511331991, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19511331991}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T20:24:48.464556+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5519001", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051622+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": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.762916+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520140", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051699+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "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": 19310950017, "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:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.769871+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520138", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051578+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "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": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.767702+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520136", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051853+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "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": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.765482+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520139", "taskType": "text-generation", "verifyResult": null} @@ -958,7 +953,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T13:03:09.363122+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:02:59.638626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T13:07:51.584082+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:05:58.860026+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688937", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T14:08:44.565999+00:00", "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {"architectures": [], "configFingerprint": "5ba0f3d0350c6aad95b8d320dd475d03180877733e000b4e0ec4e7a1a9599db3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229976064, "estimatedRequiredGiB": 4.066, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3638566160, "modelscopeLicense": "apache-2.0", "modelscopeParams": 389223169, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:dspark", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:quantized", "custom_tag:minicpmv", "custom_tag:minicpmv4.7", "custom_tag:text-generation", "custom_tag:vision-understanding", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3638566160}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T06:08:36.740120+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689542", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T14:14:07.742556+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T06:13:19.034567+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689608", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T14:51:38.748052+00:00", "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T06:49:04.032078+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689967", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T15:07:26.070090+00:00", "modelId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21000825520, "estimatedRequiredGiB": 23.484, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 21013103805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21013103805}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T07:05:46.531823+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5690178", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T15:23:24.077806+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "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": 19310950017, "modelscopeLicense": "other", "modelscopeParams": 5321729392, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T07:22:26.160574+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5690393", "taskType": "text-generation", "verifyResult": null} @@ -1039,7 +1033,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T12:23:17.227778+00:00", "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T04:21:55.761494+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5753378", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T12:23:17.227701+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["KimiLinearForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30532500512, "estimatedRequiredGiB": 34.133, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kimi_linear", "modelscopeFileSize": 30542125733, "modelscopeLicense": "mit", "modelscopeParams": 49122681728, "modelscopeTags": ["license:mit", "model_type:kimi_linear", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30542125733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T04:21:55.752785+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5753376", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T12:23:17.227785+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["KimiLinearForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54087705936, "estimatedRequiredGiB": 60.459, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kimi_linear", "modelscopeFileSize": 54097373275, "modelscopeLicense": "mit", "modelscopeParams": 49122681728, "modelscopeTags": ["license:mit", "model_type:kimi_linear", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 54097373275}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T04:23:11.655520+00:00", "targetGpu": "MetaX_c-500", "taskId": "5753396", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T12:23:17.227725+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": 15859917848, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859917848}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T04:23:11.562135+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5753394", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T12:23:17.227746+00:00", "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-10-24T04:23:11.556204+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5753395", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T15:11:52.365216+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 11.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10652847562, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "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", "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": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 10652847562}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T07:09:54.259187+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5755923", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T15:15:17.435323+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-24T07:14:56.252437+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5755982", "taskType": "text-generation", "verifyResult": null} @@ -1086,11 +1079,11 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T06:31:42.736707+00:00", "modelId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432697392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5432697392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T22:30:40.638245+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5767970", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T06:36:40.944414+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-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": 33064318294, "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": 33064318294}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T22:35:28.972746+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5768032", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T06:46:31.238453+00:00", "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-10-24T22:46:09.835164+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768204", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 7.167, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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", "repositoryOnDiskBytes": 6413020232}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:05.033296+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768501", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 16.539, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14798414872, "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": 14798414872}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:05.038732+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768505", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:05.032150+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768502", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/MiniMax-M2.5-REAP-139B-A10B-AWQ-4bit", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80093556736, "estimatedRequiredGiB": 89.546, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 80124470070, "modelscopeLicense": "other", "modelscopeParams": 139149203788, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minimax", "custom_tag:MOE", "custom_tag:pruning", "custom_tag:compression"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 80124470070}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:05.053249+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768503", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:05.082828+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768504", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T07:12:33.441010+00:00", "modelId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6397037240, "estimatedRequiredGiB": 7.167, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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", "repositoryOnDiskBytes": 6413020232}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:12:05.033296+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768501", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T07:12:33.440974+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 16.539, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14798414872, "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": 14798414872}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:12:05.038732+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768505", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T07:12:33.440868+00:00", "modelId": "cyankiwi/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:12:05.032150+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5768502", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T07:12:33.440949+00:00", "modelId": "cyankiwi/MiniMax-M2.5-REAP-139B-A10B-AWQ-4bit", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80093556736, "estimatedRequiredGiB": 89.546, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 80124470070, "modelscopeLicense": "other", "modelscopeParams": 139149203788, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minimax", "custom_tag:MOE", "custom_tag:pruning", "custom_tag:compression"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 80124470070}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:12:05.053249+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768503", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T07:12:33.440990+00:00", "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T23:12:05.082828+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768504", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["IQuestLoopCoderForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23517027912, "estimatedRequiredGiB": 26.285, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "iquestloopcoder", "modelscopeFileSize": 23519230439, "modelscopeLicense": "other", "modelscopeParams": 39794696320, "modelscopeTags": ["license:other", "model_type:iquestloopcoder", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23519230439}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:58.240562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768526", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432697392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5432697392}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T23:12:58.229897+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768525", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-10-24T23:37:28.736824+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5768837", "taskType": "text-generation", "verifyResult": null}