From f16535fb02e66ef7c3c13149072102903688e8b3 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sat, 24 Oct 2026 15:15:18 +0000 Subject: [PATCH] state: generation 34065 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 4 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 80 +++++++++---------- .modelhub_state/recovery_intents.jsonl | 12 +++ manifest.json | 18 ++--- outcomes/submissions.jsonl | 3 +- 7 files changed, 68 insertions(+), 57 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 2fdfce1591..6fdff42a72 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-24T15:13:38.540474+00:00", + "generatedAt": "2026-10-24T15:15:17.806325+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 2008938370..7b3cae9894 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-24T15:09:49.258007+00:00", + "communityAttemptedAt": "2026-10-24T15:15:17.957288+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-24T15:13:38.662090+00:00", + "generatedAt": "2026-10-24T15:15:17.957288+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index e24d4e7db4..0ae0a8de86 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-24T15:13:38.662090+00:00", + "catalogUpdatedAt": "2026-10-24T15:15:17.957288+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-24T15:13:39.947207+00:00", + "generatedAt": "2026-10-24T15:15:17.957288+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6203,6 +6203,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-24T15:13:38.662090+00:00", + "taskTreeUpdatedAt": "2026-10-24T15:15:17.957288+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index c4ebcb48d3..7e64e543cc 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-24T15:11:52.673232+00:00", - "lastSyncTime": "2026-10-24T15:11:52.365238+00:00", + "generatedAt": "2026-10-24T15:15:17.702251+00:00", + "lastSyncTime": "2026-10-24T15:15:17.435344+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2677,16 +2677,16 @@ "unresolvedFailureCount": 15 }, "Sunrise_pt-200-x1|vllm|text-generation": { - "attributableFailureCount": 635, + "attributableFailureCount": 636, "decisionFailureRate": 0.983, "decisionSuccessRate": 0.017, - "decisionTotal": 646, + "decisionTotal": 647, "failureBreakdown": { "ambiguous_runtime": 109, "architecture_compatibility": 43, "backend_operator": 33, "context_length": 34, - "framework_architecture_unsupported": 154, + "framework_architecture_unsupported": 155, "memory_capacity": 113, "platform_infrastructure": 224, "repository_structure": 75, @@ -2694,7 +2694,7 @@ "tokenizer_compatibility": 182, "参数/模板问题": 11 }, - "failureCount": 979, + "failureCount": 980, "failureRate": 0.9889, "framework": "vllm", "pendingCount": 0, @@ -2704,7 +2704,7 @@ "successRate": 0.0111, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 990, + "total": 991, "unresolvedFailureCount": 120 }, "Sunrise_pt-200-x1|vllm|unknown": { @@ -3207,17 +3207,17 @@ "unresolvedFailureCount": 6558 }, "vllm": { - "attributableFailureCount": 3718, + "attributableFailureCount": 3719, "decisionFailureRate": 0.971, "decisionSuccessRate": 0.029, - "decisionTotal": 3829, + "decisionTotal": 3830, "failureBreakdown": { "ambiguous_runtime": 1610, "architecture_compatibility": 112, "attention_backend": 3, "backend_operator": 98, "context_length": 161, - "framework_architecture_unsupported": 1428, + "framework_architecture_unsupported": 1429, "memory_capacity": 725, "model_load": 230, "platform_infrastructure": 888, @@ -3226,14 +3226,14 @@ "tokenizer_compatibility": 425, "参数/模板问题": 105 }, - "failureCount": 6321, + "failureCount": 6322, "failureRate": 0.9827, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 111, "successRate": 0.0173, - "total": 6432, + "total": 6433, "unresolvedFailureCount": 1715 }, "vllm-customized": { @@ -3384,7 +3384,7 @@ "unresolvedFailureCount": 344 } }, - "generatedAt": "2026-10-24T15:11:52.658450+00:00", + "generatedAt": "2026-10-24T15:15:17.687092+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3721,16 +3721,16 @@ "unresolvedFailureCount": 337 }, "Sunrise_pt-200-x1": { - "attributableFailureCount": 799, - "decisionFailureRate": 0.8829, - "decisionSuccessRate": 0.1171, - "decisionTotal": 905, + "attributableFailureCount": 800, + "decisionFailureRate": 0.883, + "decisionSuccessRate": 0.117, + "decisionTotal": 906, "failureBreakdown": { "ambiguous_runtime": 166, "architecture_compatibility": 44, "backend_operator": 44, "context_length": 39, - "framework_architecture_unsupported": 189, + "framework_architecture_unsupported": 190, "memory_capacity": 114, "platform_infrastructure": 260, "repository_structure": 83, @@ -3739,14 +3739,14 @@ "参数/模板问题": 235, "验证失败": 32 }, - "failureCount": 1492, + "failureCount": 1493, "failureRate": 0.9337, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 260, "successCount": 106, "successRate": 0.0663, - "total": 1598, + "total": 1599, "unresolvedFailureCount": 433 }, "Vastai_va16": { @@ -23232,16 +23232,16 @@ "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|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, "platform_infrastructure": 8, "参数/模板问题": 2 }, - "failureCount": 18, + "failureCount": 19, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", @@ -23253,7 +23253,7 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 18, + "total": 19, "unresolvedFailureCount": 2 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": { @@ -57971,15 +57971,15 @@ "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|33": { - "attributableFailureCount": 2, + "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 2, + "decisionTotal": 3, "failureBreakdown": { - "framework_architecture_unsupported": 2, + "framework_architecture_unsupported": 3, "platform_infrastructure": 4 }, - "failureCount": 6, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, @@ -57992,7 +57992,7 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 6, + "total": 7, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|34": { @@ -61791,20 +61791,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18015, - "totalRecords": 18559, + "terminalRecords": 18016, + "totalRecords": 18560, "totals": { - "attributableFailureCount": 6373, + "attributableFailureCount": 6374, "decisionFailureRate": 0.866, "decisionSuccessRate": 0.134, - "decisionTotal": 7359, + "decisionTotal": 7360, "failureBreakdown": { "ambiguous_runtime": 4673, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, "context_length": 328, - "framework_architecture_unsupported": 2367, + "framework_architecture_unsupported": 2368, "memory_capacity": 1207, "model_load": 577, "platform_infrastructure": 972, @@ -61815,14 +61815,14 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17029, + "failureCount": 17030, "failureRate": 0.9453, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0547, - "total": 18015, + "total": 18016, "unresolvedFailureCount": 9684 }, "warnings": [ @@ -61865,7 +61865,6 @@ "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 Ascend_910-b4|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 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|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 Vastai_va16|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 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。", @@ -61882,10 +61881,11 @@ "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|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 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 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 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 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18559, + "summarizedRecords": 18560, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 3bb272e3a7..628a602cb4 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3775,6 +3775,18 @@ {"batchId": "2228027dae704c78be2daf0daa1dc5a2", "completedAt": "2026-10-24T10:37:43.615540+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-24T10:37:31.819404+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fb5e5dc974ec485588e885e7074e0da5", "lastModified": "2026-10-21T17:04:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-24T15:13:46.086931+00:00", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5758988", "taskType": "text-generation"} {"batchId": "47cf257fd0984aa891d68fe8a116bbdd", "completedAt": "2026-10-24T13:54:43.036517+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T13:54:40.704268+00:00", "framework": "vllm-mlu", "intentId": "95b600dfebc8499eae650b4dd8304336", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-24T15:13:46.087790+00:00", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5761466", "taskType": "text-generation"} {"batchId": "c79618643ef849f9b1801bfe186a3b17", "completedAt": "2026-10-24T14:58:45.165782+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-24T14:58:42.702412+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9c66e4f123b6494bbde5d4c27b9ea510", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-24T15:13:46.087195+00:00", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5762276", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.723710+00:00", "framework": "vllm_tokenizer_patch", "intentId": "50e1a059314942e0a490f0859df7d8a5", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.723805+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1b5c578f61c245cba7a297bd4ffabaeb", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.723852+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba8db7fd6c654aa5a105d8e8edfa4aaa", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.723895+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2026412d16de49ee84560d9c77f17f38", "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": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.723937+00:00", "framework": "vllm_tokenizer_patch", "intentId": "612e47d3aded48a0af58c352cfaa18af", "lastModified": "2026-10-24T13:55:27+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.723979+00:00", "framework": "vllm_tokenizer_patch", "intentId": "28cd859f045d4e1592d4e87f06abe725", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.724022+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bffc10ac44db4fa1b5d7eb0f3ae9a7d6", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.724064+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7950dbd989bd4a288b15263110eee886", "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": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.724109+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1c12c2d44c1644a785300cc6eb8e352f", "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": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.724153+00:00", "framework": "vllm_fix_tokenizer", "intentId": "db26465140ea4c3d91ec0dae0257f376", "lastModified": "2026-10-24T00:34:29+00:00", "modelAddress": "https://modelscope.cn/models/ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "repoId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.724206+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f3efee464728448f82346bae6640e1b1", "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": "7c0ac134c40746ab93b15453cfe4dfbb", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:15:18.724249+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7422b57163094914b00971b9ad2913e4", "lastModified": "2026-10-24T12:36:06+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": "cd6883805d76423ba85d42db7233753e", "completedAt": "2026-10-24T15:13:43.618553+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:13:41.125337+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dfc758db95bf43c89eb679f13a798f0a", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "cd6883805d76423ba85d42db7233753e", "completedAt": "2026-10-24T15:13:43.618551+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:13:41.125296+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d787b61a60d34663a549e3e0316357b2", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "cd6883805d76423ba85d42db7233753e", "completedAt": "2026-10-24T15:13:43.618548+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-24T15:13:41.125254+00:00", "framework": "vllm_fix_tokenizer", "intentId": "759ee5869a374305a4b6afcbd2e59a2b", "repoId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "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 352f3ab9ad..7dcb406c02 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "8f473ab6899b8fbadd6f312e78f9a2233c47ecc4666d911518f7a5079c63385b", - ".modelhub_state/architecture_compatibility_blacklist.json": "dcedcac40ed92f0eee263fd387528da4d3debc4d91b7ec66891653365fd54e19", + ".modelhub_state/architecture_compatibility_blacklist.json": "536ad2402b35439961d93fb934e53562740121acd30b558e30b8844bb3af32cd", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "22428d81158296ec37472a8a7cd0478a9b03e9cf996a9cb0b29c85a8ecde937a", - ".modelhub_state/official_capabilities.json": "d7bcfe56a1c0fc0a28690b9212c034a1825bc96e4b344bb922e7b407d52d0b2e", - ".modelhub_state/outcome_checkpoint.json": "d33161922ae3bee07dd46e295ab7de0b83d03c4636d668c8dd976fb247737c02", + ".modelhub_state/market_intelligence.json": "0a86087e2762eb7d2f37b4315f830d548b9c877feb9cdd97a42c95157fe3c1ee", + ".modelhub_state/official_capabilities.json": "f420a8d5214fbe7fca190ba384c6b3ed23c68afc9667479fd94ae2adf3506264", + ".modelhub_state/outcome_checkpoint.json": "e7d7230bfd77ea475231b25cb38b292592554a97cbf76df980f3bd97aa99d2da", ".modelhub_state/queue_cleanup_latest.json": "99abbae22ce15895ca831150f6da931212ed2fc87c11635fa302ff15cdd90da3", ".modelhub_state/recent_outcomes.jsonl": "16ba5a8104f0f564b78b84a4668279dee556fce668ab2dfdb86a779520d85162", ".modelhub_state/recovery_active_tasks.jsonl": "f9808a5d150d9838fb308cef31fce43003a24af2331a246f92b04ab8723c9b68", - ".modelhub_state/recovery_intents.jsonl": "e41d4fc29be2951c50a0e9aa1979a07a160f2c2f56d4f29987808d8660c7cfa8", + ".modelhub_state/recovery_intents.jsonl": "291641fd156bf01fa8649ed0cf8ea6120c7a70b928a28cd9206a4cc144abab1e", ".modelhub_state/routing_intelligence.json": "ff008313c0d3b58c4e5d2faa84c6763a9910147f6e7f9d7966d47f4aca821802", ".modelhub_state/submission_exclusions.jsonl": "3bb99a0a703cee6767cdaeed2e3d26480ebf6d1cb44552f40bf65c94d9ed58b1", ".modelhub_state/worker_crashes.jsonl": "0202e6c82e987d7caeccc86b1ad515e3e6e72f5e974af0d95b2d6acc326133b6", "ledger/submissions.jsonl": "8eca01b62272d9e87ef663809a1da9a7813e283910085b9a588eb6a934e16377", - "outcomes/submissions.jsonl": "69f076bf6c8d14e8d4662d939600a171e99b2ca3b95fc435a33627d9084fd2ac" + "outcomes/submissions.jsonl": "5214e463c1ad98433abe0933e88f1bddb9459aeac6665f48e04b8e20065adf66" }, - "generation": 34064, - "phase": "cycle", + "generation": 34065, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-24T15:13:46.332899+00:00", + "updatedAt": "2026-10-24T15:15:18.884116+00:00", "writerId": "f3962e442a544d0aab4bb98889be6b76" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 98cdf72522..f51f01c006 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -100,7 +100,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null} {"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": "2026-09-21T00:08:58.191909+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": "2026-09-21T00:08:58.192026+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.736217+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981872", "taskType": "text-generation", "verifyResult": null} @@ -1086,7 +1085,7 @@ {"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": null, "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": "pending", "submitTime": "2026-10-24T07:14:56.252437+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5755982", "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} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5e92ea80b8a14e9d9df4a8021a55a75630c3df70ad5d06be579f5b260e3acbbe", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021920, "estimatedRequiredGiB": 35.117, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 31422264685, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:coding", "custom_tag:agent", "custom_tag:4b", "custom_tag:compact"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31422264685}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T07:32:00.888639+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5756228", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ce1b6c2fb35d8c8174d091b41f397a11f33ada0df403ec501be8f8c7b8fbbd49", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1383768224, "estimatedRequiredGiB": 1.547, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1384215789, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1291904512, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:atomic-chat", "custom_tag:qwen3.5", "custom_tag:z-lab", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1384215789}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T07:32:01.066273+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5756226", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24604826824, "estimatedRequiredGiB": 27.524, "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": 24628378863, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20349011824, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ascend", "custom_tag:ascend310p", "custom_tag:w4a8", "custom_tag:mtp", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24628378863}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T07:32:01.086834+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5756227", "taskType": "text-generation", "verifyResult": null}