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

state: generation 22119 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-08 09:18:56 +00:00
parent 5004b41510
commit 9a7590a14b
9 changed files with 2353 additions and 2372 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2382,7 +2382,7 @@
"metax_c-500|vllm|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 6,
"evidenceCount": 7,
"expiresAt": "2026-10-22T02:29:17.944417+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-22T02:29:17.944417+00:00",
@@ -2393,15 +2393,15 @@
"nkkbr/Mini-K3-1H-decay-g1-v2_B",
"nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C",
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
"nkkbr/Mini-K3-1H-decay-g2-v2_C"
],
"sourceTaskIds": [
"5011010",
"5009394",
"5009165",
"5007393",
"5007347"
"5008520",
"5007393"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
@@ -2910,7 +2910,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-08T08:53:06.829265+00:00",
"generatedAt": "2026-10-08T09:13:38.151676+00:00",
"summary": {
"activeBlockCount": 145,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-08T09:07:21.686372+00:00",
"generatedAt": "2026-10-08T09:14:57.671112+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1582
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

154
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-08T08:53:06.736240+00:00",
"lastSyncTime": "2026-10-08T08:53:06.467995+00:00",
"generatedAt": "2026-10-08T09:13:38.052090+00:00",
"lastSyncTime": "2026-10-08T09:13:37.469435+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2386,7 +2386,7 @@
"metax_c-500|vllm|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 6,
"evidenceCount": 7,
"expiresAt": "2026-10-22T02:29:17.944417+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-22T02:29:17.944417+00:00",
@@ -2397,15 +2397,15 @@
"nkkbr/Mini-K3-1H-decay-g1-v2_B",
"nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C",
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
"nkkbr/Mini-K3-1H-decay-g2-v2_C",
"nkkbr/Mini-K3-1H-decay-g16-v2_B"
"nkkbr/Mini-K3-1H-attnres-standard-v1_B",
"nkkbr/Mini-K3-1H-decay-g2-v2_C"
],
"sourceTaskIds": [
"5011010",
"5009394",
"5009165",
"5007393",
"5007347"
"5008520",
"5007393"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
@@ -4819,16 +4819,16 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 639,
"decisionFailureRate": 0.9609,
"decisionSuccessRate": 0.0391,
"decisionTotal": 665,
"attributableFailureCount": 640,
"decisionFailureRate": 0.961,
"decisionSuccessRate": 0.039,
"decisionTotal": 666,
"failureBreakdown": {
"ambiguous_runtime": 134,
"architecture_compatibility": 20,
"backend_operator": 43,
"context_length": 46,
"framework_architecture_unsupported": 202,
"framework_architecture_unsupported": 203,
"memory_capacity": 84,
"model_load": 65,
"platform_infrastructure": 3,
@@ -4837,7 +4837,7 @@
"tokenizer_compatibility": 79,
"参数/模板问题": 10
},
"failureCount": 786,
"failureCount": 787,
"failureRate": 0.968,
"framework": "vllm",
"pendingCount": 0,
@@ -4847,7 +4847,7 @@
"successRate": 0.032,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 812,
"total": 813,
"unresolvedFailureCount": 144
},
"MetaX_c-500|vllm|unknown": {
@@ -5641,17 +5641,17 @@
"unresolvedFailureCount": 6477
},
"vllm": {
"attributableFailureCount": 3681,
"attributableFailureCount": 3682,
"decisionFailureRate": 0.972,
"decisionSuccessRate": 0.028,
"decisionTotal": 3787,
"decisionTotal": 3788,
"failureBreakdown": {
"ambiguous_runtime": 1602,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 95,
"context_length": 161,
"framework_architecture_unsupported": 1401,
"framework_architecture_unsupported": 1402,
"memory_capacity": 725,
"model_load": 228,
"platform_infrastructure": 880,
@@ -5660,14 +5660,14 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 52
},
"failureCount": 6215,
"failureCount": 6216,
"failureRate": 0.9832,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 880,
"successCount": 106,
"successRate": 0.0168,
"total": 6321,
"total": 6322,
"unresolvedFailureCount": 1654
},
"vllm-customized": {
@@ -5818,7 +5818,7 @@
"unresolvedFailureCount": 304
}
},
"generatedAt": "2026-10-08T08:53:06.722272+00:00",
"generatedAt": "2026-10-08T09:13:38.033416+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 124,
@@ -6093,16 +6093,16 @@
"unresolvedFailureCount": 170
},
"MetaX_c-500": {
"attributableFailureCount": 679,
"decisionFailureRate": 0.822,
"decisionSuccessRate": 0.178,
"decisionTotal": 826,
"attributableFailureCount": 680,
"decisionFailureRate": 0.8222,
"decisionSuccessRate": 0.1778,
"decisionTotal": 827,
"failureBreakdown": {
"ambiguous_runtime": 306,
"architecture_compatibility": 21,
"backend_operator": 43,
"context_length": 59,
"framework_architecture_unsupported": 210,
"framework_architecture_unsupported": 211,
"memory_capacity": 85,
"model_load": 66,
"platform_infrastructure": 5,
@@ -6113,14 +6113,14 @@
"日志缺失": 15,
"验证失败": 48
},
"failureCount": 1472,
"failureRate": 0.9092,
"failureCount": 1473,
"failureRate": 0.9093,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 147,
"successRate": 0.0908,
"total": 1619,
"successRate": 0.0907,
"total": 1620,
"unresolvedFailureCount": 788
},
"Mthreads_s4000": {
@@ -21483,14 +21483,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|mini_k3|none": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "mini_k3",
@@ -21502,7 +21502,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|muse_glimmer|none": {
@@ -26264,10 +26264,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"model_load": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -26279,8 +26278,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -26336,16 +26335,16 @@
"unresolvedFailureCount": 16
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -26357,7 +26356,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
@@ -27264,31 +27263,6 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|cohere2|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": "2026-09-24T04:54:21.054731+00:00",
"modelType": "cohere2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -27465,15 +27439,15 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|mini_k3|none": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-10-08T03:44:24.154872+00:00",
@@ -27486,7 +27460,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|mini_k3|none": {
@@ -50956,14 +50930,14 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|mini_k3|none|30": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"framework_architecture_unsupported": 6
"framework_architecture_unsupported": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
@@ -50976,7 +50950,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|muse_glimmer|none|34": {
@@ -57496,20 +57470,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17611,
"totalRecords": 18098,
"terminalRecords": 17612,
"totalRecords": 18099,
"totals": {
"attributableFailureCount": 6290,
"attributableFailureCount": 6291,
"decisionFailureRate": 0.8653,
"decisionSuccessRate": 0.1347,
"decisionTotal": 7269,
"decisionTotal": 7270,
"failureBreakdown": {
"ambiguous_runtime": 4592,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 130,
"context_length": 327,
"framework_architecture_unsupported": 2308,
"framework_architecture_unsupported": 2309,
"memory_capacity": 1206,
"model_load": 571,
"platform_infrastructure": 955,
@@ -57520,14 +57494,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16632,
"failureCount": 16633,
"failureRate": 0.9444,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 955,
"successCount": 979,
"successRate": 0.0556,
"total": 17611,
"total": 17612,
"unresolvedFailureCount": 9387
},
"warnings": [
@@ -57537,14 +57511,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57590,6 +57564,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18098,
"summarizedRecords": 18099,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -205,6 +205,7 @@
{"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": ["mini_k3"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T22:01:50.158773+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T00:26:48.653700+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5009624", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T03:19:51.851162+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "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": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T00:10:30.409776+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009394", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T03:19:51.851040+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "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": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T23:50:56.150801+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009165", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T09:13:37.469435+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "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": null, "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": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T23:00:55.147214+00:00", "targetGpu": "MetaX_c-500", "taskId": "5008520", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383779+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T22:38:57.960315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008253", "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": "2026-10-07T18:18:51.743129+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "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": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:21:59.843515+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5008078", "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": ["mini_k3"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T20:23:14.668330+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "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": null, "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": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:14:33.594032+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008009", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-22T04:16:12.463726+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "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": "vllm", "lastSyncTime": "2026-09-24T10:56:20.956238+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.638177+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005440", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T10:53:27.671921+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "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": 9093251763}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.526740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005439", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T04:54:21.054731+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.404225+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005438", "taskType": "text-generation", "verifyResult": -1}

1162
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1790
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff