From 72d843aab32b6a8714f84eb4c944b8c21d54a824 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Thu, 22 Oct 2026 20:45:03 +0000 Subject: [PATCH] state: generation 30058 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 176 ++++++++++-------- .modelhub_state/recovery_intents.jsonl | 12 ++ manifest.json | 18 +- outcomes/submissions.jsonl | 2 - 7 files changed, 126 insertions(+), 92 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index f75e0c76be..a44704c3d2 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -487,7 +487,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-22T20:43:20.961138+00:00", + "generatedAt": "2026-10-22T20:45:01.928284+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 3067f39529..160e7e5e67 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-22T20:43:21.061139+00:00", + "generatedAt": "2026-10-22T20:45:02.057348+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 668c874f95..3c72677d87 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-22T20:43:21.061139+00:00", + "catalogUpdatedAt": "2026-10-22T20:45:02.057348+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-22T20:43:21.061139+00:00", + "generatedAt": "2026-10-22T20:45:02.057348+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6735,6 +6735,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-22T20:43:21.061139+00:00", + "taskTreeUpdatedAt": "2026-10-22T20:45:02.057348+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 424f492c13..7a0b6dcb8b 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-22T19:30:36.430282+00:00", - "lastSyncTime": "2026-10-22T19:30:36.154418+00:00", + "generatedAt": "2026-10-22T20:45:01.829689+00:00", + "lastSyncTime": "2026-10-22T20:45:01.569715+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1063,29 +1063,29 @@ "unresolvedFailureCount": 11 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation": { - "attributableFailureCount": 35, - "decisionFailureRate": 0.7955, - "decisionSuccessRate": 0.2045, - "decisionTotal": 44, + "attributableFailureCount": 36, + "decisionFailureRate": 0.8, + "decisionSuccessRate": 0.2, + "decisionTotal": 45, "failureBreakdown": { "ambiguous_runtime": 55, - "framework_architecture_unsupported": 31, + "framework_architecture_unsupported": 32, "model_load": 4, "platform_infrastructure": 1, "参数/模板问题": 5, "验证失败": 3 }, - "failureCount": 99, - "failureRate": 0.9167, + "failureCount": 100, + "failureRate": 0.9174, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, - "successRate": 0.0833, + "successRate": 0.0826, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 108, + "total": 109, "unresolvedFailureCount": 63 }, "Cambricon_mlu-370-x4|vllm|text-generation": { @@ -2661,7 +2661,7 @@ "decisionSuccessRate": 0.0138, "decisionTotal": 145, "failureBreakdown": { - "ambiguous_runtime": 3, + "ambiguous_runtime": 4, "backend_operator": 11, "framework_architecture_unsupported": 32, "memory_capacity": 1, @@ -2669,18 +2669,18 @@ "tokenizer_compatibility": 99, "参数/模板问题": 10 }, - "failureCount": 191, - "failureRate": 0.9896, + "failureCount": 192, + "failureRate": 0.9897, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 35, "successCount": 2, - "successRate": 0.0104, + "successRate": 0.0103, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 193, - "unresolvedFailureCount": 13 + "total": 194, + "unresolvedFailureCount": 14 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 635, @@ -3266,27 +3266,27 @@ "unresolvedFailureCount": 58 }, "vllm-mlu": { - "attributableFailureCount": 61, - "decisionFailureRate": 0.7349, - "decisionSuccessRate": 0.2651, - "decisionTotal": 83, + "attributableFailureCount": 62, + "decisionFailureRate": 0.7381, + "decisionSuccessRate": 0.2619, + "decisionTotal": 84, "failureBreakdown": { "ambiguous_runtime": 114, - "framework_architecture_unsupported": 53, + "framework_architecture_unsupported": 54, "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, "参数/模板问题": 47, "验证失败": 3 }, - "failureCount": 226, - "failureRate": 0.9113, + "failureCount": 227, + "failureRate": 0.9116, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0887, - "total": 248, + "successRate": 0.0884, + "total": 249, "unresolvedFailureCount": 164 }, "vllm-patch-tokenizer": { @@ -3342,7 +3342,7 @@ "decisionSuccessRate": 0.0352, "decisionTotal": 199, "failureBreakdown": { - "ambiguous_runtime": 436, + "ambiguous_runtime": 437, "backend_operator": 11, "framework_architecture_unsupported": 58, "memory_capacity": 11, @@ -3351,15 +3351,15 @@ "tokenizer_compatibility": 99, "参数/模板问题": 33 }, - "failureCount": 696, - "failureRate": 0.99, + "failureCount": 697, + "failureRate": 0.9901, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 35, "successCount": 7, - "successRate": 0.01, - "total": 703, - "unresolvedFailureCount": 469 + "successRate": 0.0099, + "total": 704, + "unresolvedFailureCount": 470 }, "vllm_tokenizer_patch": { "attributableFailureCount": 176, @@ -3390,7 +3390,7 @@ "unresolvedFailureCount": 341 } }, - "generatedAt": "2026-10-22T19:30:36.415971+00:00", + "generatedAt": "2026-10-22T20:45:01.815806+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3479,15 +3479,15 @@ "unresolvedFailureCount": 608 }, "Cambricon_mlu-370-x4": { - "attributableFailureCount": 769, - "decisionFailureRate": 0.9122, - "decisionSuccessRate": 0.0878, - "decisionTotal": 843, + "attributableFailureCount": 770, + "decisionFailureRate": 0.9123, + "decisionSuccessRate": 0.0877, + "decisionTotal": 844, "failureBreakdown": { "ambiguous_runtime": 520, "architecture_compatibility": 53, "context_length": 48, - "framework_architecture_unsupported": 321, + "framework_architecture_unsupported": 322, "memory_capacity": 219, "model_load": 8, "platform_infrastructure": 16, @@ -3497,14 +3497,14 @@ "日志缺失": 13, "验证失败": 42 }, - "failureCount": 1675, + "failureCount": 1676, "failureRate": 0.9577, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, "successRate": 0.0423, - "total": 1749, + "total": 1750, "unresolvedFailureCount": 890 }, "Cambricon_mlu-370-x8": { @@ -3732,7 +3732,7 @@ "decisionSuccessRate": 0.1174, "decisionTotal": 903, "failureBreakdown": { - "ambiguous_runtime": 165, + "ambiguous_runtime": 166, "architecture_compatibility": 44, "backend_operator": 44, "context_length": 39, @@ -3745,15 +3745,15 @@ "参数/模板问题": 233, "验证失败": 32 }, - "failureCount": 1486, - "failureRate": 0.9334, + "failureCount": 1487, + "failureRate": 0.9335, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 259, "successCount": 106, - "successRate": 0.0666, - "total": 1592, - "unresolvedFailureCount": 430 + "successRate": 0.0665, + "total": 1593, + "unresolvedFailureCount": 431 }, "Vastai_va16": { "attributableFailureCount": 471, @@ -9863,16 +9863,16 @@ "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": { - "attributableFailureCount": 8, + "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 8, + "decisionTotal": 9, "failureBreakdown": { - "framework_architecture_unsupported": 8, + "framework_architecture_unsupported": 9, "参数/模板问题": 1, "验证失败": 1 }, - "failureCount": 10, + "failureCount": 11, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", @@ -9884,7 +9884,7 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 10, + "total": 11, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": { @@ -22226,9 +22226,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen2", @@ -22240,8 +22240,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 2, @@ -37633,14 +37633,14 @@ "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|34": { - "attributableFailureCount": 2, + "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 2, + "decisionTotal": 3, "failureBreakdown": { - "framework_architecture_unsupported": 2 + "framework_architecture_unsupported": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, @@ -37653,7 +37653,7 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 2, + "total": 3, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none|34": { @@ -56058,6 +56058,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none|34": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_fix_tokenizer", + "loadSizeLog2Bucket": 34, + "modelType": "qwen2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Sunrise_pt-200-x1", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -60889,20 +60913,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17980, - "totalRecords": 18521, + "terminalRecords": 17982, + "totalRecords": 18523, "totals": { - "attributableFailureCount": 6363, - "decisionFailureRate": 0.8658, - "decisionSuccessRate": 0.1342, - "decisionTotal": 7349, + "attributableFailureCount": 6364, + "decisionFailureRate": 0.8659, + "decisionSuccessRate": 0.1341, + "decisionTotal": 7350, "failureBreakdown": { - "ambiguous_runtime": 4670, + "ambiguous_runtime": 4671, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 136, "context_length": 328, - "framework_architecture_unsupported": 2359, + "framework_architecture_unsupported": 2360, "memory_capacity": 1207, "model_load": 577, "platform_infrastructure": 971, @@ -60913,18 +60937,17 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16994, + "failureCount": 16996, "failureRate": 0.9452, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 971, "successCount": 986, "successRate": 0.0548, - "total": 17980, - "unresolvedFailureCount": 9660 + "total": 17982, + "unresolvedFailureCount": 9661 }, "warnings": [ - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", @@ -60937,6 +60960,7 @@ "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -60953,7 +60977,9 @@ "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -60978,12 +61004,10 @@ "组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" + "组合 Iluvatar_bi-150|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18521, + "summarizedRecords": 18523, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index ec4a18e818..44c95132e3 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3726,6 +3726,18 @@ {"batchId": "9189f5c453744760bed1aee56b9287af", "completedAt": "2026-10-22T17:55:09.184737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T17:54:54.518512+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2943bc61f2714655a726db5ad1db11f8", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T20:43:29.886456+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5722886", "taskType": "text-generation"} {"batchId": "d951efdc91554b1eb41d1bbf3ae1e0d7", "completedAt": "2026-10-22T20:21:06.258245+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:21:03.557699+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a36c6ca0622d46fc8f09c65b58529360", "lastModified": "2026-10-22T13:57:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "reason": null, "reconciledAt": "2026-10-22T20:43:29.885275+00:00", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5724977", "taskType": "text-generation"} {"batchId": "4da72fb9df654621af214d2580119d18", "completedAt": "2026-10-22T20:25:26.110649+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:25:23.630397+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5bcde5a40eb543eeb24ce85c99821717", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T20:43:29.885575+00:00", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5725025", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "1d8ba6e2bf36aa47c80ff7bd95383cf1571f55e0a76760eb56b3f847863afa7f", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.887698+00:00", "framework": "llamacpp", "intentId": "bec31199e63242c7b16bf73683715ebe", "lastModified": "2026-10-22T14:16:42+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5-Q8_0-GGUF", "repoId": "InternScience/Sage-A1.5-Q8_0-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.887815+00:00", "framework": "llamacpp", "intentId": "874fcd587f534bcc80cd7b07b35b3f2a", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.887871+00:00", "framework": "vllm_tokenizer_patch", "intentId": "de1569f5d9654cca98f7a1f91fc8206b", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.887925+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bed0f28da15d4d6e8ae2e8041e9a46e2", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.887976+00:00", "framework": "vllm-mlu", "intentId": "5876f1df98b34341bceba52e507f8f2e", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888029+00:00", "framework": "vllm-mlu", "intentId": "9d10597fbda34c8fb373d8b64ebaa200", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888080+00:00", "framework": "vllm-mlu", "intentId": "0cdd551030ec4502a3400cd30d5d5db7", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888130+00:00", "framework": "vllm-mlu", "intentId": "28a61670163948789e36ff80b15c4d24", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888187+00:00", "framework": "vllm_fix_tokenizer", "intentId": "455ef95d90264fbfbd46eb8c3c349f6d", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-AWQ-4bit", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888230+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d14d2111bfb64a249752e514acc96514", "lastModified": "2026-10-21T16:41:42+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888273+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e74bbfedf6ac46c78a631200fe8c70f5", "lastModified": "2026-10-21T17:13:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-4bit", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "09166e5bed6648b8a05ed1bf914eaa0e", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:45:02.888316+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7728e9a7849a43aead88eb6aef824a9d", "lastModified": "2026-10-22T13:58:47+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "7ca53c89f7fc4b07a85940815cfadef8", "completedAt": "2026-10-22T20:43:24.436504+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:43:21.678410+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d47c1f96cfa5452c8d00de6e999746fd", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "7ca53c89f7fc4b07a85940815cfadef8", "completedAt": "2026-10-22T20:43:24.436502+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:43:21.678368+00:00", "framework": "vllm_fix_tokenizer", "intentId": "65d3ed6875ef4684909052296be136b0", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "7ca53c89f7fc4b07a85940815cfadef8", "completedAt": "2026-10-22T20:43:24.436498+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:43:21.678325+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b51cc3ec76604626bc21d03f3be6f63b", "repoId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 7111b078cc..905a214f29 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "f1664cadfc5e59c0212ca3043cad47a1b74baf650147d3d8ab1adc5cc1e952c8", - ".modelhub_state/architecture_compatibility_blacklist.json": "ef31b8ed93ecfca61b3a71d6005ec9c3a8e2792e155cf200afec5bf70d95a69d", + ".modelhub_state/architecture_compatibility_blacklist.json": "3f4547a64cdfffabd46edce1118c2202027019856218fd7a8fc809c2177d51e4", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "49d910090e225872cc025c58b6425fb585c270a304ff56a6b7b6a6cdf41b9937", - ".modelhub_state/official_capabilities.json": "47c0986ecfabd78117d1bed9f1e91a06c01aa453a9f05b87c88408a51513d1a7", - ".modelhub_state/outcome_checkpoint.json": "e9c8728cf7d13bb954dcf250a71a1623dc243927b98530fe4d594acfaa8cd4fe", + ".modelhub_state/market_intelligence.json": "264995799490d8f65b1da394a050c9c884022ca9c9f0f75fea45f07e68df3afe", + ".modelhub_state/official_capabilities.json": "c39b6988a206f0800c901334c977bd69293c36b199bc7269d0bac380380d832a", + ".modelhub_state/outcome_checkpoint.json": "95f4dc653c2e06984bab52b311d1ae9524471285f8d475d248aec541ea0a744d", ".modelhub_state/queue_cleanup_latest.json": "8334310d4dead516bef55821a2fcd0ee22b747cd886dc6d77a07cf9c439bb3f9", ".modelhub_state/recent_outcomes.jsonl": "af80b03c1147019d447a3a33c5bbb83a8733c09983c2a9478b8d3b01bb7a779f", ".modelhub_state/recovery_active_tasks.jsonl": "beac9af9cb82d4a9d44444aae6e760f7b8a0fe456a8e993393a7e60f9d95e5ff", - ".modelhub_state/recovery_intents.jsonl": "63cdee0f4eba869d6c0171aa33f4b2b5da0bb03a28974547c6224a8dd8adc763", + ".modelhub_state/recovery_intents.jsonl": "7eb8849bb7ae1c76a3e62b9bae152e4ce2e1a07f26b43884884aeea7cbb67019", ".modelhub_state/routing_intelligence.json": "709aeee28ee4e6be22edf076f4cd1a962f5e759a9f0c7be93e4a25a9c4c7ef54", ".modelhub_state/submission_exclusions.jsonl": "e2677e09d968a0c44c65d7c030b9c8ea2c9d39dc378ce302c2a309ab54d600d9", ".modelhub_state/worker_crashes.jsonl": "50e3ab320d986c635b0d4cb9b1de107b33f9ab8864ff5aa9ca00e1b4af9f30cc", "ledger/submissions.jsonl": "75058d9dcbd73536cfdc1dca6b376fd788ac11a297d305cdfea88ddebf0cbadf", - "outcomes/submissions.jsonl": "a669680907a5141cf1dd65829d7e60a3e1485b9b56553dde0bfffae1ed45fea3" + "outcomes/submissions.jsonl": "1cf4547c4755f7e714b6619a53108c1a750f45629e097b3c0c696d7c80b3aa84" }, - "generation": 30057, - "phase": "cycle", + "generation": 30058, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-22T20:43:30.134537+00:00", + "updatedAt": "2026-10-22T20:45:03.043453+00:00", "writerId": "a94e2cbdfb3d4160878859cdc87771b0" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 36e1c20824..87cdf4ea75 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -103,7 +103,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192060+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.441456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981851", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192031+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "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:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.502255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981861", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191915+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.453969+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981852", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191909+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.639728+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981864", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192054+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.613984+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981862", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191935+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "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:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.664252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981866", "taskType": "text-generation", "verifyResult": null} @@ -177,7 +176,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T14:06:39.057071+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:05:15.403300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:06:39.057047+00:00", "modelId": "Youssofal/MiMo-V2.6-Qwen-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674987255, "estimatedRequiredGiB": 9.718, "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": null, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:coding", "custom_tag:agentic", "custom_tag:mimo", "custom_tag:xiaomi", "custom_tag:qwen3.5", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-air", "custom_tag:macbook-pro", "custom_tag:mac-mini", "custom_tag:opencode", "custom_tag:claude-code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695114401}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:05:15.443994+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054596", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:24:00.455827+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:21:33.668586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054819", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T15:58:05.958555+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907662447, "estimatedRequiredGiB": 20.038, "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": 17929422825, "modelscopeLicense": null, "modelscopeParams": 8953803264, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17929422825}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T07:56:37.447618+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5056005", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T21:29:59.059868+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "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": 20473981039, "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": 20473981039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T13:26:56.157380+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5062101", "taskType": "text-generation", "verifyResult": null}