diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index d391055faa..3393ae297f 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -588,7 +588,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-26T06:40:36.042427+00:00", + "generatedAt": "2026-10-26T06:42:15.528008+00:00", "summary": { "activeBlockCount": 29, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index f00d37918f..418654ef83 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-26T06:40:36.167813+00:00", + "generatedAt": "2026-10-26T06:42:15.651196+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 79f4a3a0fc..5235e5fa3a 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-26T06:40:36.167813+00:00", + "catalogUpdatedAt": "2026-10-26T06:42:15.651196+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-26T06:40:36.167813+00:00", + "generatedAt": "2026-10-26T06:42:15.651196+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6275,6 +6275,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-26T06:40:36.167813+00:00", + "taskTreeUpdatedAt": "2026-10-26T06:42:15.651196+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index fec22b5d65..ba1171fd4c 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-26T06:34:01.825271+00:00", - "lastSyncTime": "2026-10-26T06:33:59.250203+00:00", + "generatedAt": "2026-10-26T06:42:15.418598+00:00", + "lastSyncTime": "2026-10-26T06:42:12.635847+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2175,28 +2175,28 @@ "unresolvedFailureCount": 57 }, "Iluvatar_mrv-100|vllm|text-generation": { - "attributableFailureCount": 49, - "decisionFailureRate": 0.7538, - "decisionSuccessRate": 0.2462, - "decisionTotal": 65, + "attributableFailureCount": 50, + "decisionFailureRate": 0.7576, + "decisionSuccessRate": 0.2424, + "decisionTotal": 66, "failureBreakdown": { "ambiguous_runtime": 16, "framework_architecture_unsupported": 40, - "model_load": 7, + "model_load": 8, "tokenizer_compatibility": 2, "参数/模板问题": 31 }, - "failureCount": 96, - "failureRate": 0.8571, + "failureCount": 97, + "failureRate": 0.8584, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, - "successRate": 0.1429, + "successRate": 0.1416, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", - "total": 112, + "total": 113, "unresolvedFailureCount": 47 }, "Kunlunxin_p-800|unknown|text-generation": { @@ -3313,10 +3313,10 @@ "unresolvedFailureCount": 6559 }, "vllm": { - "attributableFailureCount": 3728, + "attributableFailureCount": 3729, "decisionFailureRate": 0.9708, "decisionSuccessRate": 0.0292, - "decisionTotal": 3840, + "decisionTotal": 3841, "failureBreakdown": { "ambiguous_runtime": 1611, "architecture_compatibility": 112, @@ -3325,21 +3325,21 @@ "context_length": 161, "framework_architecture_unsupported": 1432, "memory_capacity": 725, - "model_load": 234, + "model_load": 235, "platform_infrastructure": 888, "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 427, "参数/模板问题": 116 }, - "failureCount": 6343, - "failureRate": 0.9826, + "failureCount": 6344, + "failureRate": 0.9827, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 112, - "successRate": 0.0174, - "total": 6455, + "successRate": 0.0173, + "total": 6456, "unresolvedFailureCount": 1727 }, "vllm-customized": { @@ -3490,7 +3490,7 @@ "unresolvedFailureCount": 369 } }, - "generatedAt": "2026-10-26T06:34:01.805100+00:00", + "generatedAt": "2026-10-26T06:42:15.400864+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 136, @@ -3687,10 +3687,10 @@ "unresolvedFailureCount": 1208 }, "Iluvatar_mrv-100": { - "attributableFailureCount": 999, - "decisionFailureRate": 0.8495, - "decisionSuccessRate": 0.1505, - "decisionTotal": 1176, + "attributableFailureCount": 1000, + "decisionFailureRate": 0.8496, + "decisionSuccessRate": 0.1504, + "decisionTotal": 1177, "failureBreakdown": { "ambiguous_runtime": 356, "architecture_compatibility": 47, @@ -3698,7 +3698,7 @@ "context_length": 77, "framework_architecture_unsupported": 312, "memory_capacity": 219, - "model_load": 91, + "model_load": 92, "platform_infrastructure": 7, "repository_structure": 133, "runtime_memory": 1, @@ -3707,14 +3707,14 @@ "日志缺失": 6, "验证失败": 47 }, - "failureCount": 1783, + "failureCount": 1784, "failureRate": 0.9097, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, "successRate": 0.0903, - "total": 1960, + "total": 1961, "unresolvedFailureCount": 777 }, "Kunlunxin_p-800": { @@ -16943,6 +16943,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|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", + "modelType": "granite", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_mrv-100|vllm|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -28682,6 +28705,31 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|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", + "lastTerminalAt": "2026-10-26T06:42:12.635847+00:00", + "modelType": "granite", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 2, "consecutiveFailures": 2, @@ -49794,6 +49842,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|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", + "loadSizeLog2Bucket": 32, + "modelType": "granite", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Iluvatar_mrv-100|vllm|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -64944,13 +65016,13 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18146, - "totalRecords": 18690, + "terminalRecords": 18147, + "totalRecords": 18691, "totals": { - "attributableFailureCount": 6399, + "attributableFailureCount": 6400, "decisionFailureRate": 0.8664, "decisionSuccessRate": 0.1336, - "decisionTotal": 7386, + "decisionTotal": 7387, "failureBreakdown": { "ambiguous_runtime": 4713, "architecture_compatibility": 212, @@ -64959,7 +65031,7 @@ "context_length": 328, "framework_architecture_unsupported": 2379, "memory_capacity": 1207, - "model_load": 586, + "model_load": 587, "platform_infrastructure": 973, "repository_structure": 742, "runtime_memory": 101, @@ -64968,14 +65040,14 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17159, + "failureCount": 17160, "failureRate": 0.9456, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 973, "successCount": 987, "successRate": 0.0544, - "total": 18146, + "total": 18147, "unresolvedFailureCount": 9787 }, "warnings": [ @@ -65028,17 +65100,17 @@ "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18690, + "summarizedRecords": 18691, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 59952ec298..eb4fb885a4 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -294,7 +294,7 @@ {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["lfm2"], "framework": "vllm", "lastSyncTime": "2026-10-10T01:23:27.856116+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "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": "2026-10-06T09:47:41.656436+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321055", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560544+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:47:41.653611+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321051", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T12:14:09.655809+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:47:41.568827+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321049", "taskType": "text-generation", "verifyResult": null} +{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-10-26T06:42:12.635847+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "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": "2026-10-06T09:46:35.654004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321038", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560620+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.651628+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321042", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560484+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.650385+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321048", "taskType": "text-generation", "verifyResult": null} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-10-26T06:33:59.250203+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "263f4cb5e779de4b0b61f97834829c54e77136bc79bad2edf386dfd62b327794", "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": "failed", "status": "success", "submitTime": "2026-10-06T09:46:35.647771+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321044", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560665+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:46:35.575997+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321047", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 0aea8e0cd1..388ff4595b 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3912,6 +3912,18 @@ {"batchId": "c6c7b47e653540aa9ff30c6db5212b63", "completedAt": "2026-10-26T04:19:03.775975+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T04:19:01.480725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc0e62c204e742fa9a40633ce402167c", "lastModified": "2026-10-21T15:51:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-26T06:40:41.203565+00:00", "repoId": "cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5795848", "taskType": "text-generation"} {"batchId": "601fe9b0e0584b0d8d9e8d5cc699e2dd", "completedAt": "2026-10-26T06:29:23.876573+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:29:10.468369+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a5792fd3717b4089aecd94b60813310d", "lastModified": "2026-10-25T13:17:58+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "reason": null, "reconciledAt": "2026-10-26T06:40:41.201052+00:00", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5797185", "taskType": "text-generation"} {"batchId": "601fe9b0e0584b0d8d9e8d5cc699e2dd", "completedAt": "2026-10-26T06:29:23.876582+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:29:10.468500+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1bf00e3cb52a4c54b899264b4d852f00", "lastModified": "2026-10-20T14:21:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "reason": null, "reconciledAt": "2026-10-26T06:40:41.201049+00:00", "repoId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5797186", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507227+00:00", "framework": "vllm_fix_tokenizer", "intentId": "20cb0fd41718481784044fd377a68eed", "lastModified": "2026-10-21T16:25:01+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507329+00:00", "framework": "vllm_fix_tokenizer", "intentId": "85920d6fb7024975b2ca4ac3d6634044", "lastModified": "2026-10-25T15:10:11+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-MoVA-36B-A4B-FP8", "repoId": "IFM/Jais-3-MoVA-36B-A4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507375+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6eed21750d334894bbb57aefed71868f", "lastModified": "2026-10-21T16:14:40+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507419+00:00", "framework": "vllm_fix_tokenizer", "intentId": "274b0ba111674d558f25b77128ee7d7d", "lastModified": "2026-10-21T16:52:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-70B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-70B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507463+00:00", "framework": "vllm_fix_tokenizer", "intentId": "07681f4b17034f3ab6f5a6730748e9e5", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507506+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bac1ab3cb9f042beb3dfc8157b2970c2", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507549+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b348696a24384b779bd1f8b4666886b5", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507592+00:00", "framework": "vllm_fix_tokenizer", "intentId": "60f6880733434a059ef5651dfb03ed6b", "lastModified": "2026-10-21T17:19:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-8bit", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507635+00:00", "framework": "vllm_fix_tokenizer", "intentId": "39bb8d08cde841d6883b2ea473a27ea3", "lastModified": "2026-10-25T18:35:45+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nanbeige4.3-33B-FP8", "repoId": "primitive-ai/Nanbeige4.3-33B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507677+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9f9f7e48cb82482581728386a297ab7e", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507719+00:00", "framework": "vllm_fix_tokenizer", "intentId": "94c74781df274a309b765557a7831c8a", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "182a0518bb8e4a9499dad408736f7280", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:42:17.507762+00:00", "framework": "vllm_fix_tokenizer", "intentId": "eb70964834ad4ce98e6d44420fd93865", "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": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "ecf1056a6a0c40f4b30e7d4d4af05c22", "completedAt": "2026-10-26T06:40:39.392896+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:40:36.997232+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8a5d692f841e4cba98b7ea71eddb5786", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "ecf1056a6a0c40f4b30e7d4d4af05c22", "completedAt": "2026-10-26T06:40:39.392893+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:40:36.997189+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9fc7a4e0722497f856abbfdc0d98015", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "ecf1056a6a0c40f4b30e7d4d4af05c22", "completedAt": "2026-10-26T06:40:39.392890+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-26T06:40:36.997139+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6edadc9f249743c2a6a34c65352e36da", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 6f39772ded..7c69f39a6e 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "460e046e5b96997d719bad65de824a18e626cbd6e4fd47e376e8a31accabb30c", - ".modelhub_state/architecture_compatibility_blacklist.json": "368ab13adab7df8975efa82560d61d0ec615cd836871c4a102070cab54f36398", + ".modelhub_state/architecture_compatibility_blacklist.json": "a7397e9ca80988fb8fd700d3c0f175002c6acd0f8b13c82f5884233ce791e879", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "93de1219f0aa3800386be3f4801733df1e90e1cd22850a095a7a92d4ba723a34", - ".modelhub_state/official_capabilities.json": "aeb95216ebc4ee154644caf14e8371ffb69d109f792fd4d3d7f80d9152966428", - ".modelhub_state/outcome_checkpoint.json": "a7cc9f249b2f466c39cea8336b80c847849ab6553c5e8baebba5e4d25ffab03a", + ".modelhub_state/market_intelligence.json": "9b52ff8dc28a8b209c6a4f54651f2dd61b69e64034a663502a54fd731b59465f", + ".modelhub_state/official_capabilities.json": "f6434eeca2f9eafea2f7b1fdf61c48515d722d5f7f353abd56a2333fb756e0ba", + ".modelhub_state/outcome_checkpoint.json": "1760fa79cfc06533205f958e6eb4f7c0181ffeed76764c4f3dcdbb4e8159b479", ".modelhub_state/queue_cleanup_latest.json": "697c9d3694b85a56b121ba68a978a51c8e9e302e28ae675245e74f1dbccfaaf7", - ".modelhub_state/recent_outcomes.jsonl": "8eac0921b53b877aaa252124d5449c9d335c1db2f95166ead9995fa8206ee304", + ".modelhub_state/recent_outcomes.jsonl": "a6c12727c0303752d88e9787e25d07d78523fd740088ebaa0a5d0c21e79138c6", ".modelhub_state/recovery_active_tasks.jsonl": "1f66be5067dbb4774488e1b5deb547e5020f236ef9dcf1249d773a2372f7ab4d", - ".modelhub_state/recovery_intents.jsonl": "36209690d0a606de25845729e8f7f11c9c56d7adee809a6a9b86aaff26c934c1", + ".modelhub_state/recovery_intents.jsonl": "0f8d54eee3226386f6db6a88a5922b6fb573ce337e917c34e1a8c6e8e3f544f9", ".modelhub_state/routing_intelligence.json": "03284ee3117747f74e46cdd068fd597dc147e85ed96c1e827aa8ed1cbf79ad96", ".modelhub_state/submission_exclusions.jsonl": "bec721d27d733285faddfa9c457d1882988a145ee87f4fbf285ac5deb38326c9", ".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9", "ledger/submissions.jsonl": "938741a134e47ba3b9241e8ec62e91fe69ed9fa0532de6b83ecf174755b43174", - "outcomes/submissions.jsonl": "7f9bc16ccfae8b0b034a0d4dc4b1fb58c9cc6a2f3b2d263e74a70dfb2b190c75" + "outcomes/submissions.jsonl": "4e6b1aada0fc96eb28f583a33d54d13ec03327cae11b4e4d04ea39f8adfcf543" }, - "generation": 38075, - "phase": "cycle", + "generation": 38076, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-26T06:40:41.415954+00:00", + "updatedAt": "2026-10-26T06:42:17.748543+00:00", "writerId": "dffce16061d848e398e5b5b22f649ccc" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 81c6cc1618..87ca6bda57 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -369,7 +369,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953053+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.458983+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320894", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952834+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.457520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320895", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951819+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "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": "2026-10-06T09:46:35.565915+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321046", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953048+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "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": "2026-10-06T09:46:35.654004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321038", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952389+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.075531+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321064", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952714+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.150650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321070", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952155+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 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": "2026-10-06T09:47:42.149448+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321072", "taskType": "text-generation", "verifyResult": null}