From e39187b61dab191bcc742dba7ae67831a76c52be Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Wed, 21 Oct 2026 18:04:39 +0000 Subject: [PATCH] state: generation 27456 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 4 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 132 ++++++++++++++---- .modelhub_state/recent_outcomes.jsonl | 2 +- .modelhub_state/recovery_intents.jsonl | 12 ++ manifest.json | 20 +-- outcomes/submissions.jsonl | 3 +- 8 files changed, 132 insertions(+), 49 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index adc8fe69e4..929d3e59c1 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -749,7 +749,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-21T18:03:40.114068+00:00", + "generatedAt": "2026-10-21T18:04:37.988189+00:00", "summary": { "activeBlockCount": 36, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index c9669e57a1..0fa64a3127 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-21T17:58:42.547371+00:00", + "communityAttemptedAt": "2026-10-21T18:04:38.112025+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-21T18:03:40.236002+00:00", + "generatedAt": "2026-10-21T18:04:38.112025+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 060065b235..01de42248d 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-21T18:03:40.236002+00:00", + "catalogUpdatedAt": "2026-10-21T18:04:38.112025+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-21T18:03:40.236002+00:00", + "generatedAt": "2026-10-21T18:04:38.112025+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -7347,6 +7347,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-21T18:03:40.236002+00:00", + "taskTreeUpdatedAt": "2026-10-21T18:04:38.112025+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 95e2b1e462..7a1c95edea 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-21T17:52:04.369872+00:00", - "lastSyncTime": "2026-10-21T17:52:04.078870+00:00", + "generatedAt": "2026-10-21T18:04:37.880874+00:00", + "lastSyncTime": "2026-10-21T18:04:37.541467+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1455,24 +1455,24 @@ "decisionSuccessRate": 0.3421, "decisionTotal": 38, "failureBreakdown": { - "ambiguous_runtime": 58, + "ambiguous_runtime": 59, "framework_architecture_unsupported": 21, "model_load": 3, "tokenizer_compatibility": 1, "参数/模板问题": 42 }, - "failureCount": 125, - "failureRate": 0.9058, + "failureCount": 126, + "failureRate": 0.9065, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 13, - "successRate": 0.0942, + "successRate": 0.0935, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 138, - "unresolvedFailureCount": 100 + "total": 139, + "unresolvedFailureCount": 101 }, "Cambricon_mlu-370-x8|vllm|text-generation": { "attributableFailureCount": 22, @@ -3533,7 +3533,7 @@ "decisionSuccessRate": 0.275, "decisionTotal": 80, "failureBreakdown": { - "ambiguous_runtime": 111, + "ambiguous_runtime": 112, "framework_architecture_unsupported": 50, "model_load": 7, "platform_infrastructure": 1, @@ -3541,15 +3541,15 @@ "参数/模板问题": 47, "验证失败": 3 }, - "failureCount": 220, - "failureRate": 0.9091, + "failureCount": 221, + "failureRate": 0.9095, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.0909, - "total": 242, - "unresolvedFailureCount": 161 + "successRate": 0.0905, + "total": 243, + "unresolvedFailureCount": 162 }, "vllm-patch-tokenizer": { "attributableFailureCount": 69, @@ -3652,7 +3652,7 @@ "unresolvedFailureCount": 339 } }, - "generatedAt": "2026-10-21T17:52:04.352422+00:00", + "generatedAt": "2026-10-21T18:04:37.866055+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 132, @@ -3775,7 +3775,7 @@ "decisionSuccessRate": 0.1744, "decisionTotal": 86, "failureBreakdown": { - "ambiguous_runtime": 162, + "ambiguous_runtime": 163, "framework_architecture_unsupported": 58, "memory_capacity": 4, "model_load": 6, @@ -3784,15 +3784,15 @@ "参数/模板问题": 80, "验证失败": 22 }, - "failureCount": 337, - "failureRate": 0.9574, + "failureCount": 338, + "failureRate": 0.9575, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 15, - "successRate": 0.0426, - "total": 352, - "unresolvedFailureCount": 264 + "successRate": 0.0425, + "total": 353, + "unresolvedFailureCount": 265 }, "Iluvatar_bi-100": { "attributableFailureCount": 194, @@ -11509,6 +11509,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cagliostro|none": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "modelType": "cagliostro", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cohere2|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -25336,9 +25359,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "ambiguous_runtime": 4, + "ambiguous_runtime": 5, "framework_architecture_unsupported": 1, - "参数/模板问题": 15 + "参数/模板问题": 14 }, "failureCount": 20, "failureRate": 1.0, @@ -26125,6 +26148,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cagliostro|none": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "lastTerminalAt": "2026-10-21T18:04:37.541467+00:00", + "modelType": "cagliostro", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -39169,6 +39217,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cagliostro|none|28": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm-mlu", + "loadSizeLog2Bucket": 28, + "modelType": "cagliostro", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Cambricon_mlu-370-x8", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cohere2|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, @@ -59496,15 +59568,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17935, - "totalRecords": 18465, + "terminalRecords": 17936, + "totalRecords": 18466, "totals": { "attributableFailureCount": 6346, "decisionFailureRate": 0.8655, "decisionSuccessRate": 0.1345, "decisionTotal": 7332, "failureBreakdown": { - "ambiguous_runtime": 4659, + "ambiguous_runtime": 4660, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 135, @@ -59520,15 +59592,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16949, + "failureCount": 16950, "failureRate": 0.945, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 971, "successCount": 986, "successRate": 0.055, - "total": 17935, - "unresolvedFailureCount": 9632 + "total": 17936, + "unresolvedFailureCount": 9633 }, "warnings": [ "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", @@ -59591,6 +59663,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18465, + "summarizedRecords": 18466, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 34313ed814..dea5664cfa 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -162,6 +162,7 @@ {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-10-10T00:08:25.360761+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T10:15:00.656545+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5321500", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753325+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:57:50.947704+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321243", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T18:40:58.271044+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:57:50.660792+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321235", "taskType": "text-generation", "verifyResult": null} +{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-10-21T18:04:37.541467+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:57:50.659479+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321238", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255649+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:57:50.654563+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321239", "taskType": "text-generation", "verifyResult": null} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-10-21T01:51:56.458998+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:57:50.649801+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321240", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255846+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:57:50.452954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321233", "taskType": "text-generation", "verifyResult": null} @@ -297,4 +298,3 @@ {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159158+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.267901+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319934", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159226+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.264946+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319930", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159110+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.262829+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319938", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159146+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.261247+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319939", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 37b74a3fdd..54a7d27161 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3684,6 +3684,18 @@ {"batchId": "0ea11e40ac7a4faeb2f2fcddccea6e88", "completedAt": "2026-10-21T16:45:58.474349+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:45:55.868842+00:00", "framework": "vllm_tokenizer_patch", "intentId": "42693393ce334a21b320939e92cda285", "lastModified": "2026-10-21T14:24:21+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T18:03:49.281531+00:00", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5698067", "taskType": "text-generation"} {"batchId": "3b13cc1204944a97b904b7ba1b641f71", "completedAt": "2026-10-21T17:47:56.982213+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T17:47:54.545796+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d8fb07dbc4674e85b1fcbb9a01123268", "lastModified": "2026-10-21T14:42:38+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T18:03:49.279435+00:00", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5698916", "taskType": "text-generation"} {"batchId": "f5febe64fe2a4937b6ab83c8c871bfce", "completedAt": "2026-10-21T18:03:44.964845+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:03:42.273942+00:00", "framework": "vllm_tokenizer_patch", "intentId": "afcee6073c7e438da2ef058f33c675a9", "lastModified": "2026-10-21T17:04:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T18:03:49.280355+00:00", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5699141", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137073+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6c60dde3486742ac98888b5671c97c06", "lastModified": "2026-10-21T16:33:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137241+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f0777b4cf3124a3a822ca3e4a8b09e93", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137338+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f6a51a4d44984cb0a8b8d3c50de7d526", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137429+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69caf337fbfe4da3bd39af0e67c6ab68", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137518+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6451717d71a8465385901914a46a2056", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137607+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1223fb2d4070406599ff1895a1a62ab1", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137696+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f8c0d7b857a1457f87bda022fd85cd51", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137817+00:00", "framework": "vllm_tokenizer_patch", "intentId": "75aec1e2804f41e38362b9d360eb8dd6", "lastModified": "2026-10-21T15:04:03+00:00", "modelAddress": "https://modelscope.cn/models/hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "repoId": "hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "382eabb5f12e4c338b6a3865717a135e", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.137999+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e6c8503f315746d3bc9c8acbc2c80575", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.138087+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d1500196cf44752a860bd17e27766ae", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "dd549e51c3b04694b73f4d5f0ae34b1e", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:04:39.138184+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bb8e655e28734f3c9d78f8534b95fa56", "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}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "f5febe64fe2a4937b6ab83c8c871bfce", "completedAt": "2026-10-21T18:03:44.964855+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:03:42.274307+00:00", "framework": "vllm_tokenizer_patch", "intentId": "91ad96e0712546efacec5f3af8bf2229", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f5febe64fe2a4937b6ab83c8c871bfce", "completedAt": "2026-10-21T18:03:44.964853+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:03:42.274218+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9b3dd58eb79e4ab3b32c50c6f74f2d73", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f5febe64fe2a4937b6ab83c8c871bfce", "completedAt": "2026-10-21T18:03:44.964851+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:03:42.274119+00:00", "framework": "vllm_tokenizer_patch", "intentId": "74c07f8b30f94518a31c6870f643975c", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index e9cdc17147..0adfb85ea6 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "7f9cb480924a18f0fd3526c67d83586bf0cbf7474abbf0dabefdae4922fd307a", - ".modelhub_state/architecture_compatibility_blacklist.json": "ca6e18b8d423cd9beec3e2dbb442ab64ae8fbf0851103dfbfdd590b338521c32", + ".modelhub_state/architecture_compatibility_blacklist.json": "b65e419324f92ea329dc48548911ef16d690aed64cc429411a48e1e098b24b9f", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "60fddbb27afaa13df1259d2fa8af8ac14480224338ac5d8b9bc9875a1e609161", - ".modelhub_state/official_capabilities.json": "2d102437dc9ee9a4efcc9952ce1cfe4d861d7192414dc188b8b5c7f57fa86a3a", - ".modelhub_state/outcome_checkpoint.json": "d5826d5231ec62981da37aed30215b7a9fd40cb52c0cfe07cbee2e67202d9aae", + ".modelhub_state/market_intelligence.json": "989aafcb206f55de0a14fdc4a8702c4813155e1993718ad7fc10d930fee1bb71", + ".modelhub_state/official_capabilities.json": "61509830646e220f40ea070cb79d04b19598e7abc0378f62198fe308348d7c8e", + ".modelhub_state/outcome_checkpoint.json": "e482d70af5c40c026fa1d6bc289f21838edd60836ab4c12582c293a2deab2cf3", ".modelhub_state/queue_cleanup_latest.json": "eeef1b03a95c3ba09793f225207cf97d39da797a849fb43ce52f935caf481442", - ".modelhub_state/recent_outcomes.jsonl": "3673ae52114352dad426f07706b5f81512ad6bbbc57af22ba363084642154245", + ".modelhub_state/recent_outcomes.jsonl": "24ec76395955db5316ea193aa6a33685ef4c7bcace5288c8643bcccd81ff5285", ".modelhub_state/recovery_active_tasks.jsonl": "3ab51a74430964d57ddf0de8d3f5f1cedec452d0ed53402db246788ffc1f82a9", - ".modelhub_state/recovery_intents.jsonl": "128523153ab09098fab068b64a268172dc68a393cd2917393e302b2dfc5c2ade", + ".modelhub_state/recovery_intents.jsonl": "d413b271e283b3419aed95a8156b6c2ef2873001066021375b8a2f05dff1443a", ".modelhub_state/routing_intelligence.json": "f76ac0f4e1245dfe86f4c21425bd8cb3f64c7700f2b77dc89aae146efd224690", ".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc", ".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9", "ledger/submissions.jsonl": "f9b3244a10ed319d271bc4d1b8aa4c8be22609f9a1836a9c2a340ec239ea4675", - "outcomes/submissions.jsonl": "09cd60f8d6089d425307933f4efb75dbb887d851eb75612acac8d8ca8bee7944" + "outcomes/submissions.jsonl": "71a306474b9910f5a402d9ddc43f0b527476c0300beddf2733ccf5c1bbf8d8e8" }, - "generation": 27455, - "phase": "cycle", + "generation": 27456, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-21T18:03:49.487572+00:00", + "updatedAt": "2026-10-21T18:04:39.328712+00:00", "writerId": "f9d6ac09a4c14ca19fc241d193853c55" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 16d9b4a1b1..5a0f722e87 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -525,7 +525,6 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952019+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.444551+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321234", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952258+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "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": "2026-10-06T09:57:50.357060+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321232", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952910+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "eb9a83ed79f9711dceddc0b4af1fc5cfd921fcd5ee82124559cfc373fff55bf0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.454507+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321236", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952460+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.659479+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321238", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952789+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.664357+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321237", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952014+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.967998+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321245", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953011+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.763496+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321241", "taskType": "text-generation", "verifyResult": null} @@ -1082,7 +1081,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T16:11:20.642680+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3202498032, "estimatedRequiredGiB": 3.6, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 3221457919, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 3221457919}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T08:10:47.947488+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5691022", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T16:14:40.355786+00:00", "modelId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561932, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561932}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T08:13:50.255199+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5691062", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T17:53:42.338011+00:00", "modelId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3NextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 49231450912, "estimatedRequiredGiB": 55.063, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_next", "modelscopeFileSize": 49269386372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81324862720, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_next", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 49269386372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T09:52:13.230435+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5692453", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9441379272, "estimatedRequiredGiB": 10.569, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9457348916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9457348916}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T10:03:53.143948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T18:04:37.541436+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9441379272, "estimatedRequiredGiB": 10.569, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9457348916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9457348916}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T10:03:53.143948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064333187, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064333187}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:05:06.542231+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:36:29.041842+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5694581", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25339204672, "estimatedRequiredGiB": 28.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25350742978, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22705296512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25350742978}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T13:05:07.628503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null}