From 03278691670e764ea26e51410258da925914ee0e Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 26 Oct 2026 03:03:06 +0000 Subject: [PATCH] state: generation 37704 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 4 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 113 +++++++++++++----- .modelhub_state/recovery_intents.jsonl | 12 ++ manifest.json | 18 +-- outcomes/submissions.jsonl | 3 +- 7 files changed, 108 insertions(+), 50 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 0edfac2641..896617da55 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -546,7 +546,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-26T03:01:26.746709+00:00", + "generatedAt": "2026-10-26T03:03:05.732827+00:00", "summary": { "activeBlockCount": 27, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 9cd9afdcfc..20f7138176 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-26T02:57:29.463537+00:00", + "communityAttemptedAt": "2026-10-26T03:03:05.858522+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-26T03:01:26.857193+00:00", + "generatedAt": "2026-10-26T03:03:05.858522+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 2484685ad9..0aa7bd0ba9 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-26T03:01:26.857193+00:00", + "catalogUpdatedAt": "2026-10-26T03:03:05.858522+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-26T03:01:26.857193+00:00", + "generatedAt": "2026-10-26T03:03:05.858522+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6183,6 +6183,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-26T03:01:26.857193+00:00", + "taskTreeUpdatedAt": "2026-10-26T03:03:05.858522+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 04e8114079..8a2107d271 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-26T02:57:29.271027+00:00", - "lastSyncTime": "2026-10-26T02:57:28.943226+00:00", + "generatedAt": "2026-10-26T03:03:05.624014+00:00", + "lastSyncTime": "2026-10-26T03:03:05.157743+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -843,18 +843,18 @@ "unresolvedFailureCount": 17 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 40, + "attributableFailureCount": 41, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 40, + "decisionTotal": 41, "failureBreakdown": { "ambiguous_runtime": 107, - "framework_architecture_unsupported": 39, + "framework_architecture_unsupported": 40, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 39 }, - "failureCount": 187, + "failureCount": 188, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -864,7 +864,7 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 187, + "total": 188, "unresolvedFailureCount": 146 }, "Ascend_910-b4|vllm|text-generation": { @@ -3420,15 +3420,15 @@ "unresolvedFailureCount": 503 }, "vllm_tokenizer_patch": { - "attributableFailureCount": 181, - "decisionFailureRate": 0.9476, - "decisionSuccessRate": 0.0524, - "decisionTotal": 191, + "attributableFailureCount": 182, + "decisionFailureRate": 0.9479, + "decisionSuccessRate": 0.0521, + "decisionTotal": 192, "failureBreakdown": { "ambiguous_runtime": 223, "backend_operator": 17, "context_length": 10, - "framework_architecture_unsupported": 117, + "framework_architecture_unsupported": 118, "memory_capacity": 2, "model_load": 27, "platform_infrastructure": 3, @@ -3437,18 +3437,18 @@ "tokenizer_compatibility": 2, "参数/模板问题": 143 }, - "failureCount": 550, - "failureRate": 0.9821, + "failureCount": 551, + "failureRate": 0.9822, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, - "successRate": 0.0179, - "total": 560, + "successRate": 0.0178, + "total": 561, "unresolvedFailureCount": 366 } }, - "generatedAt": "2026-10-26T02:57:29.254136+00:00", + "generatedAt": "2026-10-26T03:03:05.607503+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 134, @@ -3479,14 +3479,14 @@ "unresolvedFailureCount": 275 }, "Ascend_910-b4": { - "attributableFailureCount": 340, - "decisionFailureRate": 0.8416, - "decisionSuccessRate": 0.1584, - "decisionTotal": 404, + "attributableFailureCount": 341, + "decisionFailureRate": 0.842, + "decisionSuccessRate": 0.158, + "decisionTotal": 405, "failureBreakdown": { "ambiguous_runtime": 258, "context_length": 1, - "framework_architecture_unsupported": 196, + "framework_architecture_unsupported": 197, "memory_capacity": 19, "model_load": 85, "platform_infrastructure": 3, @@ -3496,14 +3496,14 @@ "日志缺失": 14, "验证失败": 175 }, - "failureCount": 1093, + "failureCount": 1094, "failureRate": 0.9447, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 64, "successRate": 0.0553, - "total": 1157, + "total": 1158, "unresolvedFailureCount": 750 }, "Biren_166m": { @@ -5616,6 +5616,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|bananaall|none": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -32376,6 +32399,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|bananaall|none|12": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 12, + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -64205,20 +64252,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18116, - "totalRecords": 18660, + "terminalRecords": 18117, + "totalRecords": 18661, "totals": { - "attributableFailureCount": 6389, + "attributableFailureCount": 6390, "decisionFailureRate": 0.8663, "decisionSuccessRate": 0.1337, - "decisionTotal": 7375, + "decisionTotal": 7376, "failureBreakdown": { "ambiguous_runtime": 4708, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, "context_length": 328, - "framework_architecture_unsupported": 2373, + "framework_architecture_unsupported": 2374, "memory_capacity": 1207, "model_load": 586, "platform_infrastructure": 972, @@ -64229,14 +64276,14 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17130, + "failureCount": 17131, "failureRate": 0.9456, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0544, - "total": 18116, + "total": 18117, "unresolvedFailureCount": 9769 }, "warnings": [ @@ -64289,17 +64336,17 @@ "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-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_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 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 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 MetaX_c-500|vllm|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 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 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 Sunrise_pt-200-x1|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 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。", - "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 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。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18660, + "summarizedRecords": 18661, "version": 1 } diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index a2df277e20..79c4bb9ae4 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3890,6 +3890,18 @@ {"batchId": "508e0989f1724c8ba1ca2f30a62bf5fb", "completedAt": "2026-10-26T02:45:16.597539+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:45:14.394355+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b83ec5164def4956aed9770545a9b64e", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T03:01:33.007151+00:00", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5794921", "taskType": "text-generation"} {"batchId": "508e0989f1724c8ba1ca2f30a62bf5fb", "completedAt": "2026-10-26T02:45:16.597553+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:45:14.394569+00:00", "framework": "vllm_fix_tokenizer", "intentId": "35a661ed22a54ea1a474b97dd0487558", "lastModified": "2026-10-21T17:08:03+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-26T03:01:33.006130+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5794922", "taskType": "text-generation"} {"batchId": "632f43e1fd5b4bc99f213513d7009fd9", "completedAt": "2026-10-26T02:56:39.986059+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:56:26.187730+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1bf8c95ea0e6419e994a020970de3ce6", "lastModified": "2026-10-21T14:17:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T03:01:33.006521+00:00", "repoId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5795030", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681389+00:00", "framework": "vllm_tokenizer_patch", "intentId": "49f7467d1c7a48b18cb614374488b0ae", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681503+00:00", "framework": "vllm_tokenizer_patch", "intentId": "503ac33328854b87a958c23080f85c1b", "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": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681547+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f5eef2fd647145ed9bb130448e10d355", "lastModified": "2026-10-21T16:25:01+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681596+00:00", "framework": "vllm_fix_tokenizer", "intentId": "df11b459d47d4dcfbb734895e92ffb73", "lastModified": "2026-10-25T15:10:11+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-MoVA-36B-A4B-FP8", "repoId": "IFM/Jais-3-MoVA-36B-A4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681640+00:00", "framework": "vllm_fix_tokenizer", "intentId": "27ea0ebb1b6b4dc5bd4ef6c09f9d4533", "lastModified": "2026-10-21T16:52:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-70B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-70B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681683+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b25a97f8d6ec4529ae7dd1014c4665bc", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681727+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f58ecfa14594906a7237f9bc42d0aae", "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": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681771+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bb778ff80ddb48e6b67acacb31c725ae", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681813+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9a30057c8fc445beb5482ad04b6e9186", "lastModified": "2026-10-21T17:19:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-8bit", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681856+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1ea5b266802a45a481c2584fb0805d5e", "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": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681900+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4a9e709ae84e4cbdb64721d8543cbf9b", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "42555aa922b14c2da53daedf34da9c8c", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:03:06.681943+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4c7789194c2d47b79715cd2f02030ca7", "lastModified": "2026-10-21T17:00:11+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/command-a-reasoning-08-2025-AWQ-4bit", "repoId": "cyankiwi/command-a-reasoning-08-2025-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "aed94cf4427647f2af1049f9586239be", "completedAt": "2026-10-26T03:01:30.626999+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:01:27.733123+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6c8632cdceaf45c39967bb09a7d9c808", "repoId": "cyankiwi/command-a-reasoning-08-2025-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "aed94cf4427647f2af1049f9586239be", "completedAt": "2026-10-26T03:01:30.626995+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:01:27.733080+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f305cdd5804a485e9c6c2058dd54acba", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "aed94cf4427647f2af1049f9586239be", "completedAt": "2026-10-26T03:01:30.626993+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T03:01:27.733037+00:00", "framework": "vllm_fix_tokenizer", "intentId": "fd02f46eb75a4451a750fca4387f567a", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index a132753ab3..be52bde77d 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "c5672f9f7c31f9a317f81e2ebabb5d1cd78b2b1ec4cf22ea585d25cedb364698", - ".modelhub_state/architecture_compatibility_blacklist.json": "ea6c41bf60421cc9c7e051bf1c1cf0c50c39ff21b7882b787af9b23de218393e", + ".modelhub_state/architecture_compatibility_blacklist.json": "73be2c24991ce0c2821372a9be40c10232b39de909080ba3eb9d0595dde881c8", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "7546db1fe87dcbeb1768b537acf48d7f8532d8d6ee64ee96c7ab33b233a15f6f", - ".modelhub_state/official_capabilities.json": "525bbfb04cba2478305dd40b2e5f358c1f14b7477941643dc02aeada49c7ba03", - ".modelhub_state/outcome_checkpoint.json": "ab87a3be77e887546f626dde71eaa56c76fb4978214f256e327c4561558f2058", + ".modelhub_state/market_intelligence.json": "dac397134ae3b06e008152c382aada24e1c18d513b5ea0ffecfd3c9322cdee5d", + ".modelhub_state/official_capabilities.json": "a1555aed86b71b5da87dc04e373a2879c7bb186c26ffbbf4195f7f4fa882bdca", + ".modelhub_state/outcome_checkpoint.json": "2231818caa10eb3f40cfe5ce4f493e141c48fdecc0f7ee2fbbb558b654287c04", ".modelhub_state/queue_cleanup_latest.json": "a9d4c59d8958ed87776cb4385778c0b7cd1fcc0c9d0d3d1ea6b755d91cc9227c", ".modelhub_state/recent_outcomes.jsonl": "1ac1cee7b5eb9bf9cdec2f467bfb9785b758992928be2dfbd5781ca23737a23f", ".modelhub_state/recovery_active_tasks.jsonl": "8c7ab826604241185fb1585176dd73631459c8486c428e1ff432fd45b2b400e8", - ".modelhub_state/recovery_intents.jsonl": "a3c387d2ca8bbd602990b0411d3fe5cbe31033610c0e2fdfc7cc81c9bb52991f", + ".modelhub_state/recovery_intents.jsonl": "ca839448d715ccf81eb079f04f7e659d3bbbefe42a9c6d8f92aaaa5a2fe134b8", ".modelhub_state/routing_intelligence.json": "aefc35134d04cbfc07168979f5ab88d2df6b80a50b0da5fb4be999cf71c480ed", ".modelhub_state/submission_exclusions.jsonl": "3db506f4d37bc78a9069d6022969e3718fa3eb1dad129907c99f63d5a7300ba1", ".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9", "ledger/submissions.jsonl": "14f0edef2616b528c0e9288fdf3e1584bb23b0dd16b442a8ea9b966a6908a4d6", - "outcomes/submissions.jsonl": "e40eed8f32cf22c8417b3f28dcdbede81c89fee74e38a21694c433c868083c15" + "outcomes/submissions.jsonl": "a18dad6fe2419a47216e1aeb7f371a2846f0dc58251a4b0fef0cd3feb7ab88dd" }, - "generation": 37703, - "phase": "cycle", + "generation": 37704, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-26T03:01:33.236303+00:00", + "updatedAt": "2026-10-26T03:03:06.852914+00:00", "writerId": "dffce16061d848e398e5b5b22f649ccc" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 46b0ad87b7..e6e9d5b32e 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -198,7 +198,6 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-28T13:31:44.042829+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "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": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T05:24:48.147418+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5141843", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-28T13:49:59.951471+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T05:41:12.351082+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5142026", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-28T14:03:06.063872+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T05:54:29.352499+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5142202", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T02:56:17.459578+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T18:50:52.450333+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5154463", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T02:56:17.459609+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T18:50:52.443583+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5154462", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T03:14:36.161396+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:07:04.785610+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5154635", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-29T03:14:36.161388+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-28T19:08:37.345036+00:00", "targetGpu": "Vastai_va16", "taskId": "5154643", "taskType": "text-generation", "verifyResult": null} @@ -1085,7 +1084,7 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T01:25:06.540487+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T17:23:32.266960+00:00", "targetGpu": "Vastai_va16", "taskId": "5786730", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-26T02:03:00.157892+00:00", "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432701212, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5432701212}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T18:02:29.661531+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5787259", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-26T02:57:28.943196+00:00", "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-25T18:53:19.459268+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5788011", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T19:02:18.636734+00:00", "targetGpu": "Vastai_va16", "taskId": "5788201", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T03:03:05.157707+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T19:02:18.636734+00:00", "targetGpu": "Vastai_va16", "taskId": "5788201", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166417170, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17166417170}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T19:18:03.733127+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5788454", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115836146, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115836146}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T19:18:03.744688+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5788453", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T19:38:06.179287+00:00", "targetGpu": "Vastai_va16", "taskId": "5788765", "taskType": "text-generation", "verifyResult": null}