diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 8343a7217d..b2e6c65085 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-25T15:09:24.401742+00:00", + "generatedAt": "2026-10-25T15:11:03.653345+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index df460458c2..88bb4ffa6b 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-25T15:05:08.656991+00:00", + "communityAttemptedAt": "2026-10-25T15:11:03.770364+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-25T15:09:24.557741+00:00", + "generatedAt": "2026-10-25T15:11:03.770364+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 0090991a77..dac24f2ff2 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-25T15:09:24.557741+00:00", + "catalogUpdatedAt": "2026-10-25T15:11:03.770364+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-25T15:09:26.458583+00:00", + "generatedAt": "2026-10-25T15:11:05.501102+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -265,6 +265,14 @@ ], "updatedAt": "2026-10-25T14:58:20.177707+00:00" }, + "https://modelscope.cn/models/AtomicChat/Ling-3.0-flash-GGUF|2026-10-21T18:12:50+00:00|MetaX_c-500": { + "taskTypes": [ + "feature_emb", + "text-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-10-25T15:11:05.501102+00:00" + }, "https://modelscope.cn/models/AtomicChat/Ling-3.0-flash-GGUF|2026-10-21T18:12:50+00:00|Mthreads_s4000": { "taskTypes": [ "text-generation", @@ -448,14 +456,6 @@ ], "updatedAt": "2026-10-25T14:58:20.177472+00:00" }, - "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-GGUF|2026-10-21T18:16:49+00:00|MetaX_c-500": { - "taskTypes": [ - "feature_emb", - "text-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-10-25T14:49:13.199570+00:00" - }, "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-GGUF|2026-10-21T18:16:49+00:00|Sunrise_pt-200-x1": { "taskTypes": [ "text-generation" @@ -6649,6 +6649,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-25T15:09:24.557741+00:00", + "taskTreeUpdatedAt": "2026-10-25T15:11:03.770364+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 173610f77b..72cd5d4753 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-25T15:08:22.315724+00:00", - "lastSyncTime": "2026-10-25T15:08:22.042513+00:00", + "generatedAt": "2026-10-25T15:11:03.543100+00:00", + "lastSyncTime": "2026-10-25T15:11:03.242666+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1747,30 +1747,30 @@ "unresolvedFailureCount": 82 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": { - "attributableFailureCount": 56, - "decisionFailureRate": 0.7467, - "decisionSuccessRate": 0.2533, - "decisionTotal": 75, + "attributableFailureCount": 57, + "decisionFailureRate": 0.75, + "decisionSuccessRate": 0.25, + "decisionTotal": 76, "failureBreakdown": { "ambiguous_runtime": 38, "backend_operator": 6, "framework_architecture_unsupported": 31, "memory_capacity": 1, - "model_load": 8, + "model_load": 9, "runtime_memory": 10, "参数/模板问题": 28 }, - "failureCount": 122, - "failureRate": 0.8652, + "failureCount": 123, + "failureRate": 0.8662, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1348, + "successRate": 0.1338, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 141, + "total": 142, "unresolvedFailureCount": 66 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { @@ -3307,27 +3307,27 @@ "unresolvedFailureCount": 112 }, "vllm_0_17_0_corex_4_4_0": { - "attributableFailureCount": 56, - "decisionFailureRate": 0.7467, - "decisionSuccessRate": 0.2533, - "decisionTotal": 75, + "attributableFailureCount": 57, + "decisionFailureRate": 0.75, + "decisionSuccessRate": 0.25, + "decisionTotal": 76, "failureBreakdown": { "ambiguous_runtime": 38, "backend_operator": 6, "framework_architecture_unsupported": 31, "memory_capacity": 1, - "model_load": 8, + "model_load": 9, "runtime_memory": 10, "参数/模板问题": 28 }, - "failureCount": 122, - "failureRate": 0.8652, + "failureCount": 123, + "failureRate": 0.8662, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1348, - "total": 141, + "successRate": 0.1338, + "total": 142, "unresolvedFailureCount": 66 }, "vllm_fix_tokenizer": { @@ -3384,7 +3384,7 @@ "unresolvedFailureCount": 358 } }, - "generatedAt": "2026-10-25T15:08:22.300552+00:00", + "generatedAt": "2026-10-25T15:11:03.527691+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 134, @@ -3550,10 +3550,10 @@ "unresolvedFailureCount": 571 }, "Iluvatar_bi-150": { - "attributableFailureCount": 773, - "decisionFailureRate": 0.8375, - "decisionSuccessRate": 0.1625, - "decisionTotal": 923, + "attributableFailureCount": 774, + "decisionFailureRate": 0.8377, + "decisionSuccessRate": 0.1623, + "decisionTotal": 924, "failureBreakdown": { "ambiguous_runtime": 672, "architecture_compatibility": 15, @@ -3561,7 +3561,7 @@ "context_length": 29, "framework_architecture_unsupported": 264, "memory_capacity": 153, - "model_load": 128, + "model_load": 129, "platform_infrastructure": 21, "repository_structure": 99, "runtime_memory": 13, @@ -3570,14 +3570,14 @@ "日志缺失": 155, "验证失败": 30 }, - "failureCount": 2001, + "failureCount": 2002, "failureRate": 0.9303, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 150, "successRate": 0.0697, - "total": 2151, + "total": 2152, "unresolvedFailureCount": 1207 }, "Iluvatar_mrv-100": { @@ -14266,6 +14266,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|granite|none": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "model_load": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_0_17_0_corex_4_4_0", + "modelType": "granite", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -27160,6 +27183,31 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|granite|none": { + "attributableFailureCount": 1, + "consecutiveFailures": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "model_load": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_0_17_0_corex_4_4_0", + "lastTerminalAt": "2026-10-25T15:11:03.242666+00:00", + "modelType": "granite", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -44866,6 +44914,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|granite|none|32": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "model_load": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_0_17_0_corex_4_4_0", + "loadSizeLog2Bucket": 32, + "modelType": "granite", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -62574,13 +62646,13 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18082, - "totalRecords": 18626, + "terminalRecords": 18083, + "totalRecords": 18627, "totals": { - "attributableFailureCount": 6384, + "attributableFailureCount": 6385, "decisionFailureRate": 0.8662, "decisionSuccessRate": 0.1338, - "decisionTotal": 7370, + "decisionTotal": 7371, "failureBreakdown": { "ambiguous_runtime": 4698, "architecture_compatibility": 212, @@ -62589,7 +62661,7 @@ "context_length": 328, "framework_architecture_unsupported": 2370, "memory_capacity": 1207, - "model_load": 584, + "model_load": 585, "platform_infrastructure": 972, "repository_structure": 742, "runtime_memory": 101, @@ -62598,21 +62670,20 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17096, + "failureCount": 17097, "failureRate": 0.9455, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0545, - "total": 18082, + "total": 18083, "unresolvedFailureCount": 9740 }, "warnings": [ + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", @@ -62621,7 +62692,8 @@ "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Iluvatar_bi-150|transformers|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。", @@ -62669,6 +62741,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18626, + "summarizedRecords": 18627, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index aefeb509ea..53cf6d2645 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -184,6 +184,7 @@ {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-22T00:14:09.777758+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T12:10:56.958963+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353705", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-21T20:36:05.464876+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T12:10:56.760856+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353704", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-09T17:21:37.653573+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-07T11:48:13.065781+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353412", "taskType": "text-generation", "verifyResult": -1} +{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-25T15:11:03.242666+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T11:48:13.063658+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353415", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-10T09:11:32.260194+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:48:13.061782+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353409", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557073+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:48:13.058509+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353410", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.556998+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.959385+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353406", "taskType": "text-generation", "verifyResult": null} @@ -297,4 +298,3 @@ {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-25T06:46:31.238482+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:35:45.554451+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320867", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383953+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.477950+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320861", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383704+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.463228+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320862", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164495+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:45.374943+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320857", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index cf01f0beeb..d9398ef1c6 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3835,6 +3835,18 @@ {"batchId": "b0a653f36a89499b8e2c369ec8f96fe0", "completedAt": "2026-10-25T14:13:22.369050+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T14:13:20.104142+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c209d15af8134d558c7654a510c8a668", "lastModified": "2026-10-21T17:16:44+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T15:09:31.656157+00:00", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5783720", "taskType": "text-generation"} {"batchId": "e0f41b916ee84046bc9fea307b7c1a0c", "completedAt": "2026-10-25T14:50:54.483046+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T14:50:51.502765+00:00", "framework": "vllm-mlu", "intentId": "01a16e21816b42acaac03d62225f0c15", "lastModified": "2026-10-21T14:18:30+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-25T15:09:31.657557+00:00", "repoId": "cyankiwi/Orchestrator-8B-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5784519", "taskType": "text-generation"} {"batchId": "b437e6b7e1f24346a42fd166ea601230", "completedAt": "2026-10-25T15:08:35.780688+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:08:33.297324+00:00", "framework": "vllm_tokenizer_patch", "intentId": "855b11810b144065a8a652d98570576d", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T15:09:31.658844+00:00", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5784820", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.238903+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4368a857a63d4dbf82f9ee56eb8125a4", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239031+00:00", "framework": "vllm_tokenizer_patch", "intentId": "508c422fd67144569afc7b6c0255066b", "lastModified": "2026-10-21T16:02:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239081+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4d83abf7c38247a3bfdaf671bcda5054", "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": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239123+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d24bed4a33fb40e48379202641ddb130", "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": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239183+00:00", "framework": "vllm_tokenizer_patch", "intentId": "031c54f769c64b6bad267a858c850205", "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": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239224+00:00", "framework": "vllm", "intentId": "39f5fcabc6f24a56b7ac161c3b3715df", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239282+00:00", "framework": "vllm", "intentId": "f87d700f9f9e4822a802649f9d62f0ed", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239333+00:00", "framework": "vllm", "intentId": "a384e30c23e34a3db0c1ebcd64cb3744", "lastModified": "2026-10-21T16:25:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-4bit", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239382+00:00", "framework": "vllm", "intentId": "16b0e68548cd4b0f979627313e906e00", "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, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239431+00:00", "framework": "vllm", "intentId": "077ed80c7f714ff7b039adeb14e93790", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239479+00:00", "framework": "vllm", "intentId": "92b91ea2c97a4115963faca6ed3d6f4f", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} +{"batchId": "c8affe1dd5064f6cbd388d0bf44fbb1b", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:11:06.239526+00:00", "framework": "vllm", "intentId": "4123642c555e457585329cf63b6530e8", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} {"batchId": "2888a881180b4c3696255ff633940e3c", "completedAt": "2026-10-25T15:09:29.913317+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:09:27.532537+00:00", "framework": "vllm", "intentId": "d1210429805f496ab8da2c7decb8cc17", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} {"batchId": "2888a881180b4c3696255ff633940e3c", "completedAt": "2026-10-25T15:09:29.913315+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:09:27.532489+00:00", "framework": "vllm", "intentId": "db72e289a0714b2c87c598115cf9f106", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} {"batchId": "2888a881180b4c3696255ff633940e3c", "completedAt": "2026-10-25T15:09:29.913312+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-25T15:09:27.532441+00:00", "framework": "vllm", "intentId": "f17c38c98dcc433ebf8d21770d52e8e8", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 57cc7b00ff..ba31586f5b 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "8ca0c01e21d8cdc0ea6fa5f6a137b841030a065c5522b59fab6e2b3b8a709153", - ".modelhub_state/architecture_compatibility_blacklist.json": "7fb84659633ef3685483db71394e666ae5b26320876f65c2dadcdab1d5a6963b", + ".modelhub_state/architecture_compatibility_blacklist.json": "892aadf0b993773a01e766ae0b85e6acd51cf1b187046193c1f193be083e2d8f", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "19dd27868068025bf829da4c40f7eab84d954f27fa480d8aa42c6a0a6e99c956", - ".modelhub_state/official_capabilities.json": "b8cbe5ad241920e6f673348573236d3eb517b686ab460cdd21eec29c1f301303", - ".modelhub_state/outcome_checkpoint.json": "eb57d72df1c57faca64dc818824cc168a2de40c919e53bdd832e8caeb99d1f11", + ".modelhub_state/market_intelligence.json": "aef52f548a21d0c86b952e2156acbd153feb487b5d27b2058ccc9eec66283720", + ".modelhub_state/official_capabilities.json": "fdf6b465e3658c79cc264bead5a63ad7bce2d489760ed8da75aa47dafff162bc", + ".modelhub_state/outcome_checkpoint.json": "18be271e435591891f804072508d5796b7bd2bec2be2c1465593d9503ce5a040", ".modelhub_state/queue_cleanup_latest.json": "5e6385451ba16c7dd7646282a87fdf786c1d685dd4c2013dd9db51059196526d", - ".modelhub_state/recent_outcomes.jsonl": "6bcf9b8ae3b43be79e8d3832a333de12c04455e0efc6af6e2653e627f20879d9", + ".modelhub_state/recent_outcomes.jsonl": "295d02cdd19aa31a8087903ff97272cbe6bc614847d4ab4126d783ee6e2c1e49", ".modelhub_state/recovery_active_tasks.jsonl": "4b41e88774776d9b82ccf3f20a228869197b5c4dd4777332ce74fb7560a316c7", - ".modelhub_state/recovery_intents.jsonl": "f25154978fdaeacc5a24afb74b83f8ff7f24f1be3cd3c89e41ae8820a61f61c3", + ".modelhub_state/recovery_intents.jsonl": "09979d86d4a50bdfebb0d0aff467f1efdaddb53c1ecb59641568a9ffe36a31c6", ".modelhub_state/routing_intelligence.json": "33251eddb51fb1bbaacb2653495e37cfb65962cb7f5ed116b8da9de70bd5c94d", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/worker_crashes.jsonl": "0fc6c3913ba6a3ff00019bfaff56ce222acc4b192a4ed26e7f61a0bec8699b05", "ledger/submissions.jsonl": "d879389eb4275751502a645d6a768132af52b5008c9fd3611751fca28eca9daa", - "outcomes/submissions.jsonl": "0c1ca264b5135413091c9fe7a799b7ea033b440dddafd23fb6224f6f34f4babe" + "outcomes/submissions.jsonl": "197e12d92a4c8e6a0027f3e150fbca34ed26dd509c2a4fdb3cea54e0843e9644" }, - "generation": 36576, - "phase": "cycle", + "generation": 36577, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-25T15:09:31.918464+00:00", + "updatedAt": "2026-10-25T15:11:06.412249+00:00", "writerId": "7ff73e6204284f23bc2b88b7c29d21d9" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 06a217adf8..cb31133af4 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -486,7 +486,6 @@ {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668233+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "05dc104fca8c61e0b7e14c3355cdda1d22c2b6dca6c7d2ae77046a8789aa91d4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:59.077598+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353404", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668400+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:58.861235+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353401", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668372+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:58.869031+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353407", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668213+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:48:13.063658+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353415", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668322+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:48:13.053438+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353413", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668150+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:48:13.060463+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353411", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668282+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:48:13.073723+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353408", "taskType": "text-generation", "verifyResult": null} @@ -1086,7 +1085,7 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T14:04:11.169243+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-25T06:02:59.737531+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5773955", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T14:27:13.644091+00:00", "modelId": "cyankiwi/Jan-v1-4B-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": 5432695383, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5432695383}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T06:26:58.268481+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5774395", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T15:09:24.343675+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T07:09:12.869621+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5775023", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021920, "estimatedRequiredGiB": 35.117, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 31422264685, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:coding", "custom_tag:agent", "custom_tag:4b", "custom_tag:compact"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31422264685}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T07:10:06.602050+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5775036", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-25T15:11:03.242640+00:00", "modelId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021920, "estimatedRequiredGiB": 35.117, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 31422264685, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:coding", "custom_tag:agent", "custom_tag:4b", "custom_tag:compact"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31422264685}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T07:10:06.602050+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5775036", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5806978504, "estimatedRequiredGiB": 6.496, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 5812546890, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5812546890}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T09:20:23.633926+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5776685", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 9269343620, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8185253888, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9269343620}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:15:41.136812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5778062", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T10:15:41.132398+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5778059", "taskType": "text-generation", "verifyResult": null}