From 504e6da1c96620d0f2e70704294557bf247493d4 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Wed, 21 Oct 2026 12:34:41 +0000 Subject: [PATCH] state: generation 26895 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 137 ++++++------------ .modelhub_state/recent_outcomes.jsonl | 2 +- .modelhub_state/recovery_intents.jsonl | 12 ++ manifest.json | 20 +-- outcomes/submissions.jsonl | 3 +- 8 files changed, 74 insertions(+), 110 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 745df118f3..749e0553ce 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -869,7 +869,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-21T12:32:45.885882+00:00", + "generatedAt": "2026-10-21T12:34:34.327875+00:00", "summary": { "activeBlockCount": 42, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index e0b950a90a..203045acd8 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-21T12:32:45.998012+00:00", + "generatedAt": "2026-10-21T12:34:34.469466+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 44b94dd642..610553cb64 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-21T12:32:45.998012+00:00", + "catalogUpdatedAt": "2026-10-21T12:34:34.469466+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-21T12:32:45.998012+00:00", + "generatedAt": "2026-10-21T12:34:34.469466+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6696,6 +6696,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-21T12:32:45.998012+00:00", + "taskTreeUpdatedAt": "2026-10-21T12:34:34.469466+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 809c22abe8..857b6dd846 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-21T11:42:35.359702+00:00", - "lastSyncTime": "2026-10-21T11:42:35.280974+00:00", + "generatedAt": "2026-10-21T12:34:34.221624+00:00", + "lastSyncTime": "2026-10-21T12:34:33.758775+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -506,29 +506,6 @@ "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, - "iluvatar_bi-150|vllm_tokenizer_patch|text-generation|architectures:gemma4forconditionalgeneration": { - "architectureSignature": "architectures:gemma4forconditionalgeneration", - "architectures": [ - "gemma4forconditionalgeneration" - ], - "evidenceCount": 2, - "expiresAt": "2026-10-21T12:10:32.451262+00:00", - "framework": "vllm_tokenizer_patch", - "latestFailureAt": "2026-09-21T12:10:32.451262+00:00", - "latestSuccessfulAt": null, - "matchType": "architectures", - "modelType": "gemma4", - "sourceModelIds": [ - "mlx-community/gemma-4-e2b-it-OptiQ-4bit", - "mlx-community/gemma-4-e4b-it-OptiQ-4bit" - ], - "sourceTaskIds": [ - "5000554", - "5000551" - ], - "targetGpu": "Iluvatar_bi-150", - "taskType": "text-generation" - }, "iluvatar_bi-150|vllm_tokenizer_patch|text-generation|architectures:qwen3_5moeforconditionalgeneration": { "architectureSignature": "architectures:qwen3_5moeforconditionalgeneration", "architectures": [ @@ -897,7 +874,7 @@ } }, "architectureCompatibilitySummary": { - "activeBlockCount": 43, + "activeBlockCount": 42, "byGpuFramework": { "Ascend_910-b3|vllm": 2, "Ascend_910-b3|vllm_tokenizer_patch": 3, @@ -908,7 +885,7 @@ "Cambricon_mlu-370-x8|vllm-mlu": 3, "Iluvatar_bi-150|transformers": 1, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 2, - "Iluvatar_bi-150|vllm_tokenizer_patch": 2, + "Iluvatar_bi-150|vllm_tokenizer_patch": 1, "Iluvatar_mrv-100|vllm": 4, "Kunlunxin_p-800|vllm": 2, "Kunlunxin_p-800|vllm_tokenizer_patch": 1, @@ -1329,11 +1306,11 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "ambiguous_runtime": 152, + "ambiguous_runtime": 153, "memory_capacity": 1, "参数/模板问题": 5 }, - "failureCount": 158, + "failureCount": 159, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -1343,8 +1320,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 158, - "unresolvedFailureCount": 157 + "total": 159, + "unresolvedFailureCount": 158 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 50, @@ -3750,7 +3727,7 @@ "decisionSuccessRate": 0.0359, "decisionTotal": 195, "failureBreakdown": { - "ambiguous_runtime": 426, + "ambiguous_runtime": 427, "backend_operator": 11, "framework_architecture_unsupported": 56, "memory_capacity": 11, @@ -3759,15 +3736,15 @@ "tokenizer_compatibility": 97, "参数/模板问题": 30 }, - "failureCount": 679, + "failureCount": 680, "failureRate": 0.9898, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 35, "successCount": 7, "successRate": 0.0102, - "total": 686, - "unresolvedFailureCount": 456 + "total": 687, + "unresolvedFailureCount": 457 }, "vllm_tokenizer_patch": { "attributableFailureCount": 171, @@ -3798,7 +3775,7 @@ "unresolvedFailureCount": 339 } }, - "generatedAt": "2026-10-21T11:42:35.341359+00:00", + "generatedAt": "2026-10-21T12:34:34.207383+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 132, @@ -3862,7 +3839,7 @@ "decisionSuccessRate": 0.1147, "decisionTotal": 218, "failureBreakdown": { - "ambiguous_runtime": 296, + "ambiguous_runtime": 297, "backend_operator": 4, "context_length": 10, "framework_architecture_unsupported": 125, @@ -3876,15 +3853,15 @@ "日志缺失": 62, "验证失败": 27 }, - "failureCount": 799, + "failureCount": 800, "failureRate": 0.9697, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0303, - "total": 824, - "unresolvedFailureCount": 604 + "total": 825, + "unresolvedFailureCount": 605 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 766, @@ -8066,10 +8043,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 18, + "ambiguous_runtime": 19, "参数/模板问题": 1 }, - "failureCount": 19, + "failureCount": 20, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", @@ -8081,8 +8058,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 19, - "unresolvedFailureCount": 19 + "total": 20, + "unresolvedFailureCount": 20 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, @@ -25191,10 +25168,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2, + "ambiguous_runtime": 1, "参数/模板问题": 4 }, - "failureCount": 6, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -25206,8 +25183,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 6, - "unresolvedFailureCount": 6 + "total": 5, + "unresolvedFailureCount": 5 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 4, @@ -25267,10 +25244,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 8, + "ambiguous_runtime": 9, "参数/模板问题": 3 }, - "failureCount": 11, + "failureCount": 12, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, @@ -25282,8 +25259,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 11, - "unresolvedFailureCount": 11 + "total": 12, + "unresolvedFailureCount": 12 }, "Cambricon_mlu-370-x4|unknown|text-generation": { "attributableFailureCount": 0, @@ -25779,31 +25756,6 @@ } }, "recentProfileCombinationStats": { - "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gpt_oss|none": { - "attributableFailureCount": 0, - "consecutiveFailures": 0, - "decisionFailureRate": 0.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 0, - "failureBreakdown": { - "ambiguous_runtime": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm_tokenizer_patch", - "lastTerminalAt": "2026-10-04T01:37:22.760175+00:00", - "modelType": "gpt_oss", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Ascend_910-b3", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -26037,12 +25989,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { + "ambiguous_runtime": 1, "参数/模板问题": 1 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", - "lastTerminalAt": "2026-10-20T12:39:15.571321+00:00", + "lastTerminalAt": "2026-10-21T12:34:33.758775+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, @@ -26052,8 +26005,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, @@ -33613,9 +33566,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 5 + "ambiguous_runtime": 6 }, - "failureCount": 5, + "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, @@ -33628,8 +33581,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 5, - "unresolvedFailureCount": 5 + "total": 6, + "unresolvedFailureCount": 6 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, @@ -59184,15 +59137,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17922, - "totalRecords": 18451, + "terminalRecords": 17923, + "totalRecords": 18452, "totals": { "attributableFailureCount": 6342, "decisionFailureRate": 0.8654, "decisionSuccessRate": 0.1346, "decisionTotal": 7328, "failureBreakdown": { - "ambiguous_runtime": 4650, + "ambiguous_runtime": 4651, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 135, @@ -59208,15 +59161,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16936, + "failureCount": 16937, "failureRate": 0.945, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 971, "successCount": 986, "successRate": 0.055, - "total": 17922, - "unresolvedFailureCount": 9623 + "total": 17923, + "unresolvedFailureCount": 9624 }, "warnings": [ "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", @@ -59279,6 +59232,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18451, + "summarizedRecords": 18452, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 409b8f2576..5c6782042a 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -239,6 +239,7 @@ {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-12T21:59:39.775381+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.066396+00:00", "targetGpu": "Biren_166m", "taskId": "5320486", "taskType": "text-generation", "verifyResult": null} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-21T10:46:28.683876+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.062780+00:00", "targetGpu": "Biren_166m", "taskId": "5320488", "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": "2026-10-10T00:08:25.360789+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.054634+00:00", "targetGpu": "Biren_166m", "taskId": "5320485", "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": "2026-10-21T12:34:33.758775+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "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": 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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 9342812725}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:21.754792+00:00", "targetGpu": "Biren_166m", "taskId": "5320474", "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": "2026-10-14T02:59:18.156042+00:00", "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "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": 41847485419, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15008654192, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 41847485419}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:21.751371+00:00", "targetGpu": "Biren_166m", "taskId": "5320475", "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": "2026-10-09T17:44:29.077619+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 467369015}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:21.657678+00:00", "targetGpu": "Biren_166m", "taskId": "5320467", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851090+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "verifyResult": null} @@ -297,4 +298,3 @@ {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-03T21:52:42.757662+00:00", "modelId": "empero-ai/Qwen3.8-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T21:52:11+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4230414", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-03T21:52:42.757636+00:00", "modelId": "empero-ai/Qwen3.8-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T21:52:10+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4261809", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-12T18:40:58.271090+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:50.643337+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5260144", "taskType": "text-generation", "verifyResult": null} -{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T01:37:22.760175+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-03T16:15:50.370736+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260135", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 5d040cd9b7..7515bafb24 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3667,6 +3667,18 @@ {"batchId": "7b038b1630774fbdb1a65c0e9bbb2b8e", "completedAt": "2026-10-21T09:52:14.705530+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T09:52:12.174479+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7e2e33b0ce9641dbb6bf3ddd7a390222", "lastModified": "2026-10-19T18:19:51+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T12:33:01.819128+00:00", "repoId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5692453", "taskType": "text-generation"} {"batchId": "2be41a3c0ddf47fea7a18dec16f75bf1", "completedAt": "2026-10-21T10:03:54.578225+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T10:03:52.009664+00:00", "framework": "vllm_tokenizer_patch", "intentId": "72dabf7c174648c3ac50e60f466e4581", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "reason": null, "reconciledAt": "2026-10-21T12:33:01.818850+00:00", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation"} {"batchId": "ac919173e9b549668e5f79d4d4154344", "completedAt": "2026-10-21T12:05:07.909597+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:05:05.603070+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e466b3bec74f453eb1ee33b1b9ab4f6a", "lastModified": "2026-10-19T16:26:03+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T12:33:01.819126+00:00", "repoId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385526+00:00", "framework": "llamacpp", "intentId": "de098bfb2ff141e9afb6c5cc0bf0cea7", "lastModified": "2026-10-21T03:15:59+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.6-4B-GGUF", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385637+00:00", "framework": "llamacpp", "intentId": "a83124e652a84fef80b7424d223736fd", "lastModified": "2026-10-20T13:54:35+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Muse-Glimmer-30B-DFlash2-GGUF", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385700+00:00", "framework": "llamacpp", "intentId": "daae4829c473442b9f94444f9167169a", "lastModified": "2026-10-20T05:58:12+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385762+00:00", "framework": "vllm_tokenizer_patch", "intentId": "434ce22fd1c4488b82463b4bcf920f2b", "lastModified": "2026-10-19T16:59:08+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385815+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cc75ec2e832846c2bcd0884ad1afe960", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385866+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bbfb9f35f8f4209b840c1ec8cb93231", "lastModified": "2026-10-19T07:29:23+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-14B-W8A8", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385916+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9fc944d804bb4efdb786b12a9d7eaaad", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.385964+00:00", "framework": "vllm_tokenizer_patch", "intentId": "39d1a940035842499882921a0ed06010", "lastModified": "2026-10-19T18:55:19+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-2.1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.386013+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a3a54821467e444fb074dab41e67eda3", "lastModified": "2026-10-19T07:32:17+00:00", "modelAddress": "https://modelscope.cn/models/StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "repoId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.386061+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b0a20fed4ff44556ac908ce8c0150c47", "lastModified": "2026-10-19T21:32:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Agents-A1-AWQ-NVFP4", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.386109+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b67df1d2671a40f399a5310c1961cfcc", "lastModified": "2026-10-19T18:17:12+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "repoId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "d683dac37f05468b994fba775d644b96", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:34:41.386149+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb7fe80957d049d9bfbc2b4adc40be2e", "lastModified": "2026-10-18T15:27:59+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-27B-OptiQ-4bit", "repoId": "mlx-community/Qwen3.6-27B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "fe9177f4084d4abe82add9eeceaef85a", "completedAt": "2026-10-21T12:32:59.021072+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:32:56.460633+00:00", "framework": "vllm_tokenizer_patch", "intentId": "61ba641291f149079e738de679fa7f52", "repoId": "mlx-community/Qwen3.6-27B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "fe9177f4084d4abe82add9eeceaef85a", "completedAt": "2026-10-21T12:32:59.021069+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:32:56.460591+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8e5f33faa71f49a7a8a50aa18fd0b5b7", "repoId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "fe9177f4084d4abe82add9eeceaef85a", "completedAt": "2026-10-21T12:32:59.021066+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:32:56.460534+00:00", "framework": "vllm_tokenizer_patch", "intentId": "496159f97e584e789428a2b2d5e90722", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index ab2d71232e..9fa650deab 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "6d3d0131705f6c8c3f7576476de2831030c5edc0d86ef5dd445f594596378e66", - ".modelhub_state/architecture_compatibility_blacklist.json": "c0eacf1051efcd6207e149113462f2122069192db5f011e53ba8f48a88ee22e2", + ".modelhub_state/architecture_compatibility_blacklist.json": "f7eba9fbf3767c720ef250e662b9619f9b8359c4d6ce3837c3d42d12370ca70e", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "1676dcce1bff239065729d5fde8c2a5cf4141799864bff0f541339d5c20f2d93", - ".modelhub_state/official_capabilities.json": "3d129a28938b009634c5c3db9484306c40e60e5a7319c3603586e2f4282aa8a4", - ".modelhub_state/outcome_checkpoint.json": "1eca1fdb307935b8726a5359b1268d259aca7cae6a43cd9ac541c5dc6b07bdb5", + ".modelhub_state/market_intelligence.json": "7d549b4ccce922de608ed6b675fa2f9e70ec8100ed942bebd1a67e05cde2144f", + ".modelhub_state/official_capabilities.json": "f54b5514e877601af2d78433020c939fcecdc9cb9bd821df98484b5a13d6db85", + ".modelhub_state/outcome_checkpoint.json": "bb7e6b99d91976f22f5559c5ef589ddf7b3a46b15f1837304dee357c4b02b145", ".modelhub_state/queue_cleanup_latest.json": "67a11704905ce4b4303cf204224a1eaa8325b0cef009ef0bbc75dfd11b896f9b", - ".modelhub_state/recent_outcomes.jsonl": "0debddb689e605ebce7b25dc593b566f63bbe040c9d619b8d4d181b5b7875699", + ".modelhub_state/recent_outcomes.jsonl": "68f5f94c7213a40f434769c5ca8c77b1acf3207fadc10d349572f447c7cc5792", ".modelhub_state/recovery_active_tasks.jsonl": "0501a1905398df91d16d609e7a8d8412e6eac9b5a566e1536bac466b74efd141", - ".modelhub_state/recovery_intents.jsonl": "89fe8a09890e1eac91fbeb23e3e2f383ed90934bb5239d7b28879bbb713d15e2", + ".modelhub_state/recovery_intents.jsonl": "f6265cbcf06a31bd4be10229b0db7d0b2e2d85a276a89ed80249549d18540a25", ".modelhub_state/routing_intelligence.json": "f1852955534e7c7d5f0096ab324fc06baa0a6aa4d8228cda9ddc5690082dcb6b", ".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc", ".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9", "ledger/submissions.jsonl": "1f9a38e252b07c8ea4dc0c54e97b246384b35954816c6980445e0097189deae7", - "outcomes/submissions.jsonl": "69809ccfc108315c999b67395a85b6da43d418ff15e8fc0bbcac8093c4bc48ad" + "outcomes/submissions.jsonl": "e1029102b112eb932d69b63a1492063bc8babba6929f4e32ed05954ba211f1b1" }, - "generation": 26894, - "phase": "cycle", + "generation": 26895, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-21T12:33:02.057320+00:00", + "updatedAt": "2026-10-21T12:34:41.545107+00:00", "writerId": "f9d6ac09a4c14ca19fc241d193853c55" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 5e9e921697..1653ae1a08 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -416,7 +416,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952000+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.674379+00:00", "targetGpu": "Biren_166m", "taskId": "5320468", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952449+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "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": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.749482+00:00", "targetGpu": "Biren_166m", "taskId": "5320478", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952241+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.752927+00:00", "targetGpu": "Biren_166m", "taskId": "5320476", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952777+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "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": 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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.754792+00:00", "targetGpu": "Biren_166m", "taskId": "5320474", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952558+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "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": 1769900320, "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.760855+00:00", "targetGpu": "Biren_166m", "taskId": "5320477", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952675+00:00", "modelId": "NovelAI/novelai-lm-3b-508k", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12175174048, "estimatedRequiredGiB": 33.616, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 30079174063, "modelscopeLicense": "gpl-2.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30079174063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.860245+00:00", "targetGpu": "Biren_166m", "taskId": "5320479", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952883+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.952740+00:00", "targetGpu": "Biren_166m", "taskId": "5320483", "taskType": "text-generation", "verifyResult": null} @@ -1083,7 +1082,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T11:16:42.531453+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T03:12:14.747473+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5687332", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T11:31:04.115959+00:00", "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {"architectures": [], "configFingerprint": "02e187e3671a31235c75c7c9ad7c52e86e0476bdc3118ddf379ddb46a07261d1", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229976064, "estimatedRequiredGiB": 4.066, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3638566160, "modelscopeLicense": "apache-2.0", "modelscopeParams": 389223169, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:dspark", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:quantized", "custom_tag:minicpmv", "custom_tag:minicpmv4.7", "custom_tag:text-generation", "custom_tag:vision-understanding", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3638566160}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T03:30:34.676745+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5687537", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T11:44:31.060430+00:00", "modelId": "bartowski/OpenPathAI_Orbit-3.2-Nano-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "fc78709d4e85c217c994d6286e817ec9d9eae27c62f744569fd17a8b92fdf5ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1602349632, "estimatedRequiredGiB": 46.16, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41303483913, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation", "custom_tag:indonesian", "custom_tag:lfm2.5", "custom_tag:liquid", "custom_tag:fine-tuned", "custom_tag:sft", "custom_tag:instruction-tuning", "custom_tag:closed-qa", "custom_tag:reasoning", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41303483913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T03:43:19.854852+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5687774", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a176de7307e2dc61f89a2b7736f608cc72777b656ee1791a550289b9666f12a7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2697198592, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943398}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T04:34:20.747882+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688529", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T12:34:33.758750+00:00", "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a176de7307e2dc61f89a2b7736f608cc72777b656ee1791a550289b9666f12a7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2697198592, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T04:34:20.747882+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688529", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ", "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": 18115852009, "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": 18115852009}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T04:36:03.335412+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688559", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "a7a7d00616db408ae5c0df2a7cb156b93da7e857ba3eeb80a28825bbcf98f013", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3493762176, "estimatedRequiredGiB": 37.765, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 33791316398, "modelscopeLicense": "mit", "modelscopeParams": 3286633962, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:gguf", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle", "custom_tag:gguf", "custom_tag:ollama", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33791316398}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T05:02:59.629168+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5688914", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T05:02:59.638626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}