CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 11540 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 15:54:39 +00:00
parent 426025eb1a
commit cd3ab70ece
9 changed files with 1762 additions and 1767 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1202,7 +1202,7 @@
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:41:49.472121+00:00",
"framework": "vllm-patch-tokenizer",
"latestFailureAt": "2026-09-20T03:41:49.472121+00:00",
@@ -1210,12 +1210,10 @@
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-e2b-it-OptiQ-4bit",
"mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit"
"mlx-community/gemma-4-e2b-it-OptiQ-4bit"
],
"sourceTaskIds": [
"4970033",
"4969662"
"4970033"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -2732,7 +2730,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T15:33:46.463097+00:00",
"generatedAt": "2026-09-21T15:54:38.271429+00:00",
"summary": {
"activeBlockCount": 137,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T15:53:52.755291+00:00",
"generatedAt": "2026-09-21T15:54:38.286276+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T15:53:52.755291+00:00",
"catalogUpdatedAt": "2026-09-21T15:54:38.286276+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T15:54:21.784903+00:00",
"generatedAt": "2026-09-21T15:54:38.286276+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6649,6 +6649,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T15:53:52.755291+00:00",
"taskTreeUpdatedAt": "2026-09-21T15:54:38.286276+00:00",
"version": 1
}

122
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T15:17:58.482139+00:00",
"lastSyncTime": "2026-09-21T15:17:58.391613+00:00",
"generatedAt": "2026-09-21T15:54:38.201498+00:00",
"lastSyncTime": "2026-09-21T15:54:37.859039+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1206,7 +1206,7 @@
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:41:49.472121+00:00",
"framework": "vllm-patch-tokenizer",
"latestFailureAt": "2026-09-20T03:41:49.472121+00:00",
@@ -1214,12 +1214,10 @@
"matchType": "model_type",
"modelType": "gemma4",
"sourceModelIds": [
"mlx-community/gemma-4-e2b-it-OptiQ-4bit",
"mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit"
"mlx-community/gemma-4-e2b-it-OptiQ-4bit"
],
"sourceTaskIds": [
"4970033",
"4969662"
"4970033"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -3189,23 +3187,23 @@
"decisionSuccessRate": 0.2632,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 29,
"model_load": 11,
"tokenizer_compatibility": 2
},
"failureCount": 52,
"failureRate": 0.7761,
"failureCount": 53,
"failureRate": 0.7794,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2239,
"successRate": 0.2206,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 67,
"unresolvedFailureCount": 10
"total": 68,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -5388,7 +5386,7 @@
"decisionSuccessRate": 0.0243,
"decisionTotal": 3619,
"failureBreakdown": {
"ambiguous_runtime": 1485,
"ambiguous_runtime": 1486,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5402,15 +5400,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 45
},
"failureCount": 5926,
"failureCount": 5927,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6014,
"unresolvedFailureCount": 1530
"total": 6015,
"unresolvedFailureCount": 1531
},
"vllm-customized": {
"attributableFailureCount": 4,
@@ -5556,7 +5554,7 @@
"unresolvedFailureCount": 91
}
},
"generatedAt": "2026-09-21T15:17:58.471978+00:00",
"generatedAt": "2026-09-21T15:54:38.191412+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 95,
@@ -5618,7 +5616,7 @@
"decisionSuccessRate": 0.1202,
"decisionTotal": 208,
"failureBreakdown": {
"ambiguous_runtime": 162,
"ambiguous_runtime": 163,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 117,
@@ -5632,15 +5630,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 650,
"failureCount": 651,
"failureRate": 0.963,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.037,
"total": 675,
"unresolvedFailureCount": 465
"total": 676,
"unresolvedFailureCount": 466
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 716,
@@ -7929,9 +7927,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -7943,8 +7941,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
@@ -16504,16 +16502,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 2,
"model_load": 4,
"tokenizer_compatibility": 1
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T05:07:16.468545+00:00",
"lastTerminalAt": "2026-09-21T15:54:37.859021+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -16521,8 +16519,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 7
"total": 15,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -17070,17 +17068,17 @@
"unresolvedFailureCount": 9
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"framework_architecture_unsupported": 1,
"repository_structure": 1
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null,
@@ -17092,7 +17090,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 3,
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
@@ -17534,12 +17532,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T01:08:25.664308+00:00",
"lastTerminalAt": "2026-09-21T15:54:37.859021+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -17549,8 +17547,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 1,
@@ -20384,15 +20382,15 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-09-21T14:32:55.759813+00:00",
@@ -20405,7 +20403,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|mpt|none": {
@@ -23385,9 +23383,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
@@ -23400,8 +23398,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|llama|none|30": {
"attributableFailureCount": 1,
@@ -35435,15 +35433,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16302,
"totalRecords": 16490,
"terminalRecords": 16303,
"totalRecords": 16491,
"totals": {
"attributableFailureCount": 5890,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6836,
"failureBreakdown": {
"ambiguous_runtime": 3959,
"ambiguous_runtime": 3960,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 103,
@@ -35459,31 +35457,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15356,
"failureCount": 15357,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.058,
"total": 16302,
"unresolvedFailureCount": 8541
"total": 16303,
"unresolvedFailureCount": 8542
},
"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。",
@@ -35523,6 +35521,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16490,
"summarizedRecords": 16491,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -58,6 +58,7 @@
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T02:38:57.372787+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079201", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:15:17.867390+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457986", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556193+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T01:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079972", "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", "lastSyncTime": "2026-09-21T15:54:37.859021+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "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": 9093251901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T00:00:11.334848+00:00", "targetGpu": "Biren_166m", "taskId": "4989991", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-20T23:43:40.271809+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T23:43:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610385", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T23:08:35.573428+00:00", "modelId": "YOYO-AI/ZYH-LLM-Qwen2.5-14B-V2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T23:05:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079190", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-20T22:43:47.754964+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:31:23+00:00", "targetGpu": "Biren_166m", "taskId": "4610366", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T14:32:55.759786+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:32.578530+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969666", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:37:54.215258+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 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": "failed", "status": "success", "submitTime": "2026-09-20T03:25:32.546681+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969665", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:37:54.215238+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "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": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:32.539673+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969663", "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-patch-tokenizer", "lastSyncTime": "2026-09-21T14:32:55.759821+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "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:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:32.538500+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969662", "taskType": "text-generation", "verifyResult": -1}

1330
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2030
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff