From f62b19a38b36034403c0582aecdc85b25c9a06c3 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 22:14:30 +0000 Subject: [PATCH] state: generation 11820 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 82 +++++++++---------- .modelhub_state/recent_outcomes.jsonl | 2 +- .modelhub_state/recovery_intents.jsonl | 2 + manifest.json | 20 ++--- outcomes/submissions.jsonl | 1 - 8 files changed, 59 insertions(+), 58 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 4e171ce3e0..431e3a6a44 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -2848,7 +2848,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-21T22:12:58.282462+00:00", + "generatedAt": "2026-09-21T22:14:20.585415+00:00", "summary": { "activeBlockCount": 143, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 75f5015c16..9d69235029 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -434,7 +434,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-21T22:12:36.263798+00:00", + "generatedAt": "2026-09-21T22:14:30.398286+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index d4293e5a07..22bb4d53ea 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-21T22:12:36.263798+00:00", + "catalogUpdatedAt": "2026-09-21T22:14:30.398286+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-21T22:12:36.263798+00:00", + "generatedAt": "2026-09-21T22:14:30.398286+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6833,6 +6833,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-21T22:12:36.263798+00:00", + "taskTreeUpdatedAt": "2026-09-21T22:14:30.398286+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 22aa2afabe..e4e7e65ed9 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-21T22:12:58.204983+00:00", - "lastSyncTime": "2026-09-21T22:12:57.959636+00:00", + "generatedAt": "2026-09-21T22:14:20.512734+00:00", + "lastSyncTime": "2026-09-21T22:14:20.164578+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -3285,9 +3285,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 43 + "ambiguous_runtime": 44 }, - "failureCount": 43, + "failureCount": 44, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -3297,8 +3297,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 43, - "unresolvedFailureCount": 43 + "total": 44, + "unresolvedFailureCount": 44 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 44, @@ -5630,7 +5630,7 @@ "decisionSuccessRate": 0.0391, "decisionTotal": 128, "failureBreakdown": { - "ambiguous_runtime": 202, + "ambiguous_runtime": 203, "backend_operator": 8, "framework_architecture_unsupported": 23, "memory_capacity": 7, @@ -5639,15 +5639,15 @@ "tokenizer_compatibility": 82, "参数/模板问题": 13 }, - "failureCount": 355, + "failureCount": 356, "failureRate": 0.9861, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 17, "successCount": 5, "successRate": 0.0139, - "total": 360, - "unresolvedFailureCount": 215 + "total": 361, + "unresolvedFailureCount": 216 }, "vllm_tokenizer_patch": { "attributableFailureCount": 78, @@ -5677,7 +5677,7 @@ "unresolvedFailureCount": 120 } }, - "generatedAt": "2026-09-21T22:12:58.193583+00:00", + "generatedAt": "2026-09-21T22:14:20.502368+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 99, @@ -5739,7 +5739,7 @@ "decisionSuccessRate": 0.1185, "decisionTotal": 211, "failureBreakdown": { - "ambiguous_runtime": 184, + "ambiguous_runtime": 185, "backend_operator": 4, "context_length": 10, "framework_architecture_unsupported": 120, @@ -5753,15 +5753,15 @@ "日志缺失": 62, "验证失败": 27 }, - "failureCount": 675, + "failureCount": 676, "failureRate": 0.9643, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0357, - "total": 700, - "unresolvedFailureCount": 487 + "total": 701, + "unresolvedFailureCount": 488 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 717, @@ -8140,9 +8140,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 4 + "ambiguous_runtime": 5 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", @@ -8154,8 +8154,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 4 + "total": 5, + "unresolvedFailureCount": 5 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 0, @@ -18621,9 +18621,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 4 + "ambiguous_runtime": 5 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T22:12:57.959611+00:00", @@ -18636,8 +18636,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 4 + "total": 5, + "unresolvedFailureCount": 5 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 0, @@ -21128,9 +21128,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2 + "ambiguous_runtime": 1 }, - "failureCount": 2, + "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:21:49.901876+00:00", @@ -21143,8 +21143,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 1, + "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, @@ -24712,9 +24712,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2 + "ambiguous_runtime": 3 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, @@ -24727,8 +24727,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 0, @@ -38392,15 +38392,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16423, - "totalRecords": 16617, + "terminalRecords": 16424, + "totalRecords": 16618, "totals": { "attributableFailureCount": 5921, "decisionFailureRate": 0.8619, "decisionSuccessRate": 0.1381, "decisionTotal": 6870, "failureBreakdown": { - "ambiguous_runtime": 4043, + "ambiguous_runtime": 4044, "architecture_compatibility": 212, "attention_backend": 1, "backend_operator": 105, @@ -38416,31 +38416,31 @@ "日志缺失": 719, "验证失败": 674 }, - "failureCount": 15474, + "failureCount": 15475, "failureRate": 0.9422, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 925, "successCount": 949, "successRate": 0.0578, - "total": 16423, - "unresolvedFailureCount": 8628 + "total": 16424, + "unresolvedFailureCount": 8629 }, "warnings": [ "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "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 Ascend_910-b3 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 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 Ascend_910-b4 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Iluvatar_bi-150|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 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 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。", @@ -38480,6 +38480,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 16617, + "summarizedRecords": 16618, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 6d1bc1e24b..146b01c1c5 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -101,6 +101,7 @@ {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559353+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:53:47.320072+00:00", "targetGpu": "Biren_166m", "taskId": "4987553", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T19:45:40.057911+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "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:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:48:13.967563+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4987442", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559306+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:39:13.053978+00:00", "targetGpu": "Biren_166m", "taskId": "4987256", "taskType": "text-generation", "verifyResult": -1} +{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:14:20.164578+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:35:36.766659+00:00", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:05:56.949093+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:35:36.652541+00:00", "targetGpu": "Biren_166m", "taskId": "4987186", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:05:56.949067+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:33:46.481514+00:00", "targetGpu": "Biren_166m", "taskId": "4987185", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559123+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:33:30.958684+00:00", "targetGpu": "Biren_166m", "taskId": "4987157", "taskType": "text-generation", "verifyResult": -1} @@ -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": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901731+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "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:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.464742+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970359", "taskType": "text-generation", "verifyResult": -1} {"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": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.902144+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "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:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.460457+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970350", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556133+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:58:35.458351+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970351", "taskType": "text-generation", "verifyResult": null} -{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902097+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.457045+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970357", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 68091f9fdf..970beaf5d9 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2318,6 +2318,8 @@ {"batchId": "284d8f82865b4e9fa5349c4162079ef8", "completedAt": "2026-09-21T22:06:50.903961+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T22:06:49.703994+00:00", "framework": "vllm-mlu", "intentId": "e9661bc5313d4518935d855a3593ce2d", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "reason": null, "reconciledAt": "2026-09-21T22:13:10.593032+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007911", "taskType": "text-generation"} {"batchId": "284d8f82865b4e9fa5349c4162079ef8", "completedAt": "2026-09-21T22:06:50.903983+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T22:06:49.704122+00:00", "framework": "vllm_fix_tokenizer", "intentId": "99042884f97d4c839bbe82cfd42b9872", "lastModified": "2026-09-21T18:39:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "reason": null, "reconciledAt": "2026-09-21T22:13:10.594259+00:00", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5007912", "taskType": "text-generation"} {"batchId": "4af6f2f9dddb4facb6df3b6a82f82d3c", "completedAt": "2026-09-21T22:12:40.367441+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T22:12:39.214180+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ceaa19c09019499e868a5415aad6ea6c", "lastModified": "2026-09-21T20:13:14+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "reason": null, "reconciledAt": "2026-09-21T22:13:10.594034+00:00", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "5007978", "taskType": "text-generation"} +{"batchId": "61f048a3ac524a63be857b49853def0d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T22:14:30.721017+00:00", "framework": "vllm-patch-tokenizer", "intentId": "68b9fa38622842df9a224e510ee23c38", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "61f048a3ac524a63be857b49853def0d", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T22:14:30.721107+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e27968b92ab445eea2305f0cfd67cc99", "lastModified": "2026-09-21T18:45:44+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} {"batchId": "24082fb4e4bc48b988e1e4deac30068b", "completedAt": "2026-09-21T20:36:17.828196+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:36:00.461127+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7ef98d8672514b6cb8bcf83850090ffe", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 471803de36..cd6eb626e5 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.20.2", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "c4a309454c8150a0dad094254c339abdc8eedfab3be0cf4b57c101d27093b86e", + ".modelhub_state/architecture_compatibility_blacklist.json": "712e7e9ea7f840197d1a617e85a6f8dd33ff22f732e38f64fc56215236db448d", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "04ab6b29de009b485c37039eae05fe44a3af90fecdd8c7cfb130d2264b621fca", - ".modelhub_state/official_capabilities.json": "3bcc108433d33859e656b95480c096af21cba32ae25ef9064b10b32f666d23b0", - ".modelhub_state/outcome_checkpoint.json": "6f7cd527f67f385ec844b22902fbd65705a7df030ec2e3638aaafb96c7600aee", + ".modelhub_state/market_intelligence.json": "b82ce9816dec748fb3753304b9ed57ad3ee83c8f15ae987447a25faaedb572d0", + ".modelhub_state/official_capabilities.json": "9410acb954b679a3beac19770fe68760186fc37ad8a6070a8cdc07a9e5bae447", + ".modelhub_state/outcome_checkpoint.json": "dc3dcabf3fdcc5c424034677a72bb688175a16afc937bfab506fcaf069f9f0df", ".modelhub_state/queue_cleanup_latest.json": "684035bc75f3dccb9a852d9244b8cb34bfbaacc084ca3256703fc8b0e9da3555", - ".modelhub_state/recent_outcomes.jsonl": "f7532676cb2f855d73d43e8d4782ca9f28155333cc3176930ecb9b9e960802e5", + ".modelhub_state/recent_outcomes.jsonl": "b1886a922aa0fc3038a46ebc243eebc83179112acc31d9ff646d4550e2066d7f", ".modelhub_state/recovery_active_tasks.jsonl": "1c585566f046147956089f8190143732239458e067fdfb2864cce9bcd7fcd141", - ".modelhub_state/recovery_intents.jsonl": "4dfd33b732148c1d15369618cd7ba9f227178f4325d24a517fcd63cb24c20ccd", + ".modelhub_state/recovery_intents.jsonl": "2617e858875637721eaa0cf4b5c9c3f868f12a8500bf05b065aee229e7237fe3", ".modelhub_state/routing_intelligence.json": "db022535af31747f4d9b6284fd4c02edda2030b47daf15a8b94d9c22dc40094e", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "cbb1ab7741b32f29848ded5bcc03699fa363032e86a1a58a87cfccb3e011520d", - "outcomes/submissions.jsonl": "44642ec3b7416a84c410584d2d2255de1dd9896b33c5b8abf08134ed9ace50f4" + "outcomes/submissions.jsonl": "65807fa03c3713dcaacc4cd7626292693e7ec5f184edae75551a39cb3e675f1e" }, - "generation": 11819, - "phase": "cycle_no_slots", + "generation": 11820, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T22:13:10.778147+00:00", + "updatedAt": "2026-09-21T22:14:30.880840+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 51fc869c81..c1468e4673 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -745,7 +745,6 @@ {"failReason": null, "framework": "transformers", "lastSyncTime": "2026-09-21T04:11:57.967122+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:09:24.460163+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986875", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569189+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "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:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:33:04.562192+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987155", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569103+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:33:04.573215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987156", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T04:36:00.569153+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:35:36.766659+00:00", "targetGpu": "Biren_166m", "taskId": "4987187", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T04:51:55.164788+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:41:37.494440+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4987371", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T04:51:55.164995+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:43:36.176091+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4987372", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T04:51:55.164947+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "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": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T20:48:13.965272+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4987441", "taskType": "text-generation", "verifyResult": null}