diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 8fa1b22358..19839d339d 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-25T01:27:24.740685+00:00", + "generatedAt": "2026-10-25T01:29:02.643307+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index fe9a9f8064..ba548513f7 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,5 +1,5 @@ { - "communityAttemptedAt": "2026-10-25T01:22:28.173661+00:00", + "communityAttemptedAt": "2026-10-25T01:29:02.776930+00:00", "communityError": "ModelHubAPIError: 分页大小不能超过100", "communitySample": {}, "communityUpdatedAt": null, @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-25T01:27:24.862355+00:00", + "generatedAt": "2026-10-25T01:29:02.776930+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 1b74b38372..06aa01a02f 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-25T01:27:24.862355+00:00", + "catalogUpdatedAt": "2026-10-25T01:29:02.776930+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-25T01:27:24.862355+00:00", + "generatedAt": "2026-10-25T01:29:02.776930+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6670,6 +6670,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-25T01:27:24.862355+00:00", + "taskTreeUpdatedAt": "2026-10-25T01:29:02.776930+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 4144e980cd..d15a48450f 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-25T00:47:15.085052+00:00", - "lastSyncTime": "2026-10-25T00:47:14.556583+00:00", + "generatedAt": "2026-10-25T01:29:02.543500+00:00", + "lastSyncTime": "2026-10-25T01:29:02.231191+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1752,7 +1752,7 @@ "decisionSuccessRate": 0.2533, "decisionTotal": 75, "failureBreakdown": { - "ambiguous_runtime": 37, + "ambiguous_runtime": 38, "backend_operator": 6, "framework_architecture_unsupported": 31, "memory_capacity": 1, @@ -1760,18 +1760,18 @@ "runtime_memory": 10, "参数/模板问题": 27 }, - "failureCount": 120, - "failureRate": 0.8633, + "failureCount": 121, + "failureRate": 0.8643, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1367, + "successRate": 0.1357, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 139, - "unresolvedFailureCount": 64 + "total": 140, + "unresolvedFailureCount": 65 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 9, @@ -3312,7 +3312,7 @@ "decisionSuccessRate": 0.2533, "decisionTotal": 75, "failureBreakdown": { - "ambiguous_runtime": 37, + "ambiguous_runtime": 38, "backend_operator": 6, "framework_architecture_unsupported": 31, "memory_capacity": 1, @@ -3320,15 +3320,15 @@ "runtime_memory": 10, "参数/模板问题": 27 }, - "failureCount": 120, - "failureRate": 0.8633, + "failureCount": 121, + "failureRate": 0.8643, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1367, - "total": 139, - "unresolvedFailureCount": 64 + "successRate": 0.1357, + "total": 140, + "unresolvedFailureCount": 65 }, "vllm_fix_tokenizer": { "attributableFailureCount": 194, @@ -3384,7 +3384,7 @@ "unresolvedFailureCount": 351 } }, - "generatedAt": "2026-10-25T00:47:15.070671+00:00", + "generatedAt": "2026-10-25T01:29:02.529963+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3555,7 +3555,7 @@ "decisionSuccessRate": 0.1625, "decisionTotal": 923, "failureBreakdown": { - "ambiguous_runtime": 671, + "ambiguous_runtime": 672, "architecture_compatibility": 15, "backend_operator": 12, "context_length": 29, @@ -3570,15 +3570,15 @@ "日志缺失": 155, "验证失败": 30 }, - "failureCount": 1999, + "failureCount": 2000, "failureRate": 0.9302, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 150, "successRate": 0.0698, - "total": 2149, - "unresolvedFailureCount": 1205 + "total": 2150, + "unresolvedFailureCount": 1206 }, "Iluvatar_mrv-100": { "attributableFailureCount": 995, @@ -14540,6 +14540,29 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|plamo3|none": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_0_17_0_corex_4_4_0", + "modelType": "plamo3", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -26101,9 +26124,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { - "ambiguous_runtime": 4, + "ambiguous_runtime": 5, "framework_architecture_unsupported": 2, - "参数/模板问题": 14 + "参数/模板问题": 13 }, "failureCount": 20, "failureRate": 1.0, @@ -27064,6 +27087,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|plamo3|none": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_0_17_0_corex_4_4_0", + "lastTerminalAt": "2026-10-25T01:29:02.231191+00:00", + "modelType": "plamo3", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -44940,6 +44988,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|plamo3|none|30": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_0_17_0_corex_4_4_0", + "loadSizeLog2Bucket": 30, + "modelType": "plamo3", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -62023,15 +62095,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18046, - "totalRecords": 18590, + "terminalRecords": 18047, + "totalRecords": 18591, "totals": { "attributableFailureCount": 6374, "decisionFailureRate": 0.866, "decisionSuccessRate": 0.134, "decisionTotal": 7360, "failureBreakdown": { - "ambiguous_runtime": 4680, + "ambiguous_runtime": 4681, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, @@ -62047,20 +62119,21 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17060, + "failureCount": 17061, "failureRate": 0.9454, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0546, - "total": 18046, - "unresolvedFailureCount": 9714 + "total": 18047, + "unresolvedFailureCount": 9715 }, "warnings": [ "GPU Ascend_910-b4 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 Cambricon_mlu-370-x8 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 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 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。", @@ -62068,9 +62141,8 @@ "GPU Biren_166m 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 Cambricon_mlu-370-x4 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "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 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -62118,6 +62190,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18590, + "summarizedRecords": 18591, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index a24a04d961..3c23f2bc88 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -151,6 +151,7 @@ {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557117+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:29:02.592829+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360293", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557053+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:29:02.584970+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360291", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-24T15:31:00.652243+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "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": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:29:02.583748+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360295", "taskType": "text-generation", "verifyResult": null} +{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-25T01:29:02.231191+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-07T19:29:02.582010+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360292", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557009+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:29:02.575012+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360298", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-21T12:36:20.265435+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "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": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T19:29:02.360067+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360299", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-10T09:11:32.260219+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:29:02.288614+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360290", "taskType": "text-generation", "verifyResult": null} @@ -297,4 +298,3 @@ {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T03:40:15.756923+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:23.045201+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320526", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164596+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.872487+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320519", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164485+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.868041+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320517", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164473+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 41c506f32d..d10cdb2515 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3806,6 +3806,18 @@ {"batchId": "b58bd86e18574e0bb7215690132ffcd3", "completedAt": "2026-10-24T23:40:06.871486+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:40:04.552069+00:00", "framework": "vllm_fix_tokenizer", "intentId": "07a9702166fe4aa8b56883193253abfc", "lastModified": "2026-10-21T16:06:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T01:27:30.512725+00:00", "repoId": "cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5768869", "taskType": "text-generation"} {"batchId": "dd46d85091594fc299ddd69610e01630", "completedAt": "2026-10-25T00:50:53.380153+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T00:50:51.058404+00:00", "framework": "vllm_tokenizer_patch", "intentId": "205025f9ba3a4c7aaac9487419fd412a", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T01:27:30.513452+00:00", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5769793", "taskType": "text-generation"} {"batchId": "bc33246133c2444091b9bbcb1674a2f4", "completedAt": "2026-10-25T00:55:00.775329+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T00:54:58.482993+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ce962a7548854786870e6d6b2c94db90", "lastModified": "2026-10-24T13:55:27+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "reason": null, "reconciledAt": "2026-10-25T01:27:30.514753+00:00", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5769872", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379239+00:00", "framework": "vllm-mlu", "intentId": "f99106b4d92a486eac0430c1f8321ebe", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379349+00:00", "framework": "vllm-mlu", "intentId": "fc18f63ed7d34a31953051fbcc18b249", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379403+00:00", "framework": "vllm-mlu", "intentId": "97a3ed02029f44f39f6af7dc331fd2d3", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379453+00:00", "framework": "vllm-mlu", "intentId": "3d2a0ee0ac56408ba5ea8300fa6bf5b6", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379502+00:00", "framework": "vllm_fix_tokenizer", "intentId": "492f96255c0c47868c22ada54f8bc15c", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-AWQ-4bit", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379547+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d003dbca399b45c3b2c228f8b3492977", "lastModified": "2026-10-21T16:41:42+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379591+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ed4737d61eb14895aedb9ee9992ae3d2", "lastModified": "2026-10-24T00:34:29+00:00", "modelAddress": "https://modelscope.cn/models/ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "repoId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379634+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bfab9730fc8b4c3184dcba2689b716a4", "lastModified": "2026-10-21T17:13:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-4bit", "repoId": "cyankiwi/OmniCoder-9B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379676+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8b6bb420d20a48208b024a47f3eca4cc", "lastModified": "2026-10-24T12:36:06+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379718+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9071a392673d43e7a77b57605f39c048", "lastModified": "2026-10-21T17:16:44+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379761+00:00", "framework": "vllm_fix_tokenizer", "intentId": "294ce33554c04681a77cf9c9cead7424", "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": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "931a7b59d611438ea98c887d6d91e052", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:29:09.379803+00:00", "framework": "vllm_fix_tokenizer", "intentId": "40a56f4eef0c4e378e394d4d9f4c587a", "lastModified": "2026-10-21T17:21:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "2be4c8edd59e45039a4dd610ef81a7e8", "completedAt": "2026-10-25T01:27:28.463584+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:27:26.060029+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e4bc8450efb4034907989306d480493", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "2be4c8edd59e45039a4dd610ef81a7e8", "completedAt": "2026-10-25T01:27:28.463580+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:27:26.059987+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cfdcb02f259745cfa44ff4996fada956", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "2be4c8edd59e45039a4dd610ef81a7e8", "completedAt": "2026-10-25T01:27:28.463577+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T01:27:26.059945+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b637b065e83e455e88b6c46fb67c572c", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index a0a7c046f8..a56df41572 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "77d3b763b6ee9a33990d31a67e65f76846b5a4dc74eea928f42b3cf17bcc4828", - ".modelhub_state/architecture_compatibility_blacklist.json": "fdcfe354a20bc6ef57e94d34ee60e121bc2c42cc96fc2f3714178fae94bd176a", + ".modelhub_state/architecture_compatibility_blacklist.json": "0be601485a033cae1fc50fb13ba55364734466130906e6b6fc1e2a67313f993d", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "26bc982110e1e79b9ae43a423d76391e58b54739820cea15ef78725fd1484b31", - ".modelhub_state/official_capabilities.json": "ce41b9739096d06f8dc5fb043c6bd7eb18d0ddb42da39aa4e206cfc9851fd01c", - ".modelhub_state/outcome_checkpoint.json": "42b916d11aa3336978fb7312d162fa90091b7bb78557da7972f0da1cde336c85", + ".modelhub_state/market_intelligence.json": "887815bb589ad960fe53ad6696b25463bc7201c3515091e3599874ee741d82f8", + ".modelhub_state/official_capabilities.json": "a9b116f059f41b15bb0f138800bcc9eff16d745662fca5d9b208bde6fec8fd15", + ".modelhub_state/outcome_checkpoint.json": "588b1da059d6ba38923440b056c35b5b17cbfa81d511e16178a72225271b6dda", ".modelhub_state/queue_cleanup_latest.json": "c5f2f6b66a45af8932430af43c17d60c92c612aa90b2d9a8c8d880b10cb4548a", - ".modelhub_state/recent_outcomes.jsonl": "2b47eefbc791922c41ffc311ff358f029dc9d79c2e9f617bb9298f6c1d0c8b60", + ".modelhub_state/recent_outcomes.jsonl": "f84d3dac786fa7d8be1d76b12834d3849dcc11c4a4ce9a49d72d7f555ba5d361", ".modelhub_state/recovery_active_tasks.jsonl": "6446f13689ab39df495464ab352386bf35d9ed16cc8c3e96e8e9a5a04876ed0b", - ".modelhub_state/recovery_intents.jsonl": "c4e64eb00ed479a7402fa12f721d52a886e05c1ddea9f55c67c59437f3a4a764", + ".modelhub_state/recovery_intents.jsonl": "c8859d3394ca0e24cc948c54e509f571f7254d441b29d47820340737f24fa1dc", ".modelhub_state/routing_intelligence.json": "af13a05e16d3e43ee5e4c4ce24115a8056159f252aa53c43e61ff5cea6379581", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/worker_crashes.jsonl": "e436652d39bca5bcba31822ff9fb949a9d7ff0b7f509c170e258a53d7e01ce9a", "ledger/submissions.jsonl": "326168f5b31f4f0f898d70954fa021302795d91aeeb5e57c85db3f99b68991bf", - "outcomes/submissions.jsonl": "3c6f93f7aee61117a141dd9659b4c8a0fb6fdcb3a62dd7c2cde227cd2c36778c" + "outcomes/submissions.jsonl": "e526f777fec749023513dba9d71906f33a37b0d74ffb781c001e3211f5de45ca" }, - "generation": 35119, - "phase": "cycle", + "generation": 35120, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-25T01:27:30.710828+00:00", + "updatedAt": "2026-10-25T01:29:09.553015+00:00", "writerId": "5c9906c400e2442789cb0c734d70dc03" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index bd2d2cb4e7..3d5d7772f2 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -554,7 +554,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T03:44:24.154732+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-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": 809580753, "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": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:18:39.454725+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5360137", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154916+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:29:02.366207+00:00", "targetGpu": "Biren_166m", "taskId": "5360289", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154806+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:29:02.276855+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360297", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154885+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "pending", "status": "waiting", "submitTime": "2026-10-07T19:29:02.582010+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360292", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154812+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:29:02.569687+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360296", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154788+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": "2026-10-07T19:30:29.844294+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360307", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154949+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "df879293d64bd4eef168b273fb4b6ac51b0bec98b1555859d64582b13249914c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.942926+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360312", "taskType": "text-generation", "verifyResult": null} @@ -1087,7 +1086,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T00:07:35.841307+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 21404443971, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21404443971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T16:06:45.349812+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5763338", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T00:12:36.448725+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T16:12:09.964702+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5763434", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T00:47:14.556558+00:00", "modelId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5368163296, "estimatedRequiredGiB": 6.019, "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": 5386102118, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5386102118}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T16:46:24.637751+00:00", "targetGpu": "MetaX_c-500", "taskId": "5763860", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115836146, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115836146}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T17:28:41.168154+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5764371", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T01:29:02.231151+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115836146, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115836146}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T17:28:41.168154+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5764371", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "InternScience/Sage-A1.5-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365363088, "estimatedRequiredGiB": 44.025, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 39392487901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39392487901}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T17:55:08.331226+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5764732", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T18:41:25.446286+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5765199", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-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": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:08:37.639861+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766311", "taskType": "text-generation", "verifyResult": null}