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

state: generation 22003 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 23:42:18 +00:00
parent 099c1f2a9d
commit fc6b9293cc
9 changed files with 2377 additions and 2374 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -943,7 +943,7 @@
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 3,
"expiresAt": "2026-10-21T19:52:49.757664+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-09-21T19:52:49.757664+00:00",
@@ -952,10 +952,12 @@
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
"nkkbr/Mini-K3-1H-decay-g2-v2_C"
],
"sourceTaskIds": [
"5006516",
"5006518",
"5006512"
],
"targetGpu": "Cambricon_mlu-370-x8",
@@ -2880,7 +2882,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-07T23:17:42.860827+00:00",
"generatedAt": "2026-10-07T23:36:57.612899+00:00",
"summary": {
"activeBlockCount": 145,
"byGpuFramework": {

6
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-10-07T23:19:15.769719+00:00",
"communityAttemptedAt": "2026-10-07T23:38:20.969622+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-10-07T23:19:15.769719+00:00",
"communityUpdatedAt": "2026-10-07T23:38:20.969622+00:00",
"frameworkAttemptedAt": "2026-10-07T20:58:42.772583+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T23:33:17.267156+00:00",
"generatedAt": "2026-10-07T23:38:20.969622+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1534
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

144
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T23:17:42.770324+00:00",
"lastSyncTime": "2026-10-07T23:17:42.455387+00:00",
"generatedAt": "2026-10-07T23:36:57.524328+00:00",
"lastSyncTime": "2026-10-07T23:36:57.259705+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -947,7 +947,7 @@
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 3,
"expiresAt": "2026-10-21T19:52:49.757664+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-09-21T19:52:49.757664+00:00",
@@ -956,10 +956,12 @@
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
"nkkbr/Mini-K3-1H-attnres-block6-v1_C",
"nkkbr/Mini-K3-1H-decay-g2-v2_C"
],
"sourceTaskIds": [
"5006516",
"5006518",
"5006512"
],
"targetGpu": "Cambricon_mlu-370-x8",
@@ -3587,28 +3589,28 @@
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 21,
"decisionFailureRate": 0.6176,
"decisionSuccessRate": 0.3824,
"decisionTotal": 34,
"attributableFailureCount": 22,
"decisionFailureRate": 0.6286,
"decisionSuccessRate": 0.3714,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 54,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"model_load": 3,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 78,
"failureRate": 0.8571,
"failureCount": 79,
"failureRate": 0.8587,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1429,
"successRate": 0.1413,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 91,
"total": 92,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -5661,27 +5663,27 @@
"unresolvedFailureCount": 51
},
"vllm-mlu": {
"attributableFailureCount": 47,
"decisionFailureRate": 0.6812,
"decisionSuccessRate": 0.3188,
"decisionTotal": 69,
"attributableFailureCount": 48,
"decisionFailureRate": 0.6857,
"decisionSuccessRate": 0.3143,
"decisionTotal": 70,
"failureBreakdown": {
"ambiguous_runtime": 103,
"framework_architecture_unsupported": 39,
"framework_architecture_unsupported": 40,
"model_load": 7,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 158,
"failureRate": 0.8778,
"failureCount": 159,
"failureRate": 0.8785,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1222,
"total": 180,
"successRate": 0.1215,
"total": 181,
"unresolvedFailureCount": 110
},
"vllm-patch-tokenizer": {
@@ -5785,7 +5787,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-07T23:17:42.752835+00:00",
"generatedAt": "2026-10-07T23:36:57.510845+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 121,
@@ -5902,13 +5904,13 @@
"unresolvedFailureCount": 856
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 67,
"decisionFailureRate": 0.8171,
"decisionSuccessRate": 0.1829,
"decisionTotal": 82,
"attributableFailureCount": 68,
"decisionFailureRate": 0.8193,
"decisionSuccessRate": 0.1807,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 158,
"framework_architecture_unsupported": 54,
"framework_architecture_unsupported": 55,
"memory_capacity": 4,
"model_load": 6,
"platform_infrastructure": 2,
@@ -5916,14 +5918,14 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 290,
"failureRate": 0.9508,
"failureCount": 291,
"failureRate": 0.951,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0492,
"total": 305,
"successRate": 0.049,
"total": 306,
"unresolvedFailureCount": 221
},
"Iluvatar_bi-100": {
@@ -13429,14 +13431,14 @@
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "mini_k3",
@@ -13448,7 +13450,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": {
@@ -25546,11 +25548,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 12,
"ambiguous_runtime": 11,
"context_length": 3,
"framework_architecture_unsupported": 4
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -25562,8 +25564,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 12
"total": 18,
"unresolvedFailureCount": 11
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -25824,17 +25826,17 @@
"unresolvedFailureCount": 16
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3
"framework_architecture_unsupported": 4
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -25846,7 +25848,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation": {
@@ -26382,9 +26384,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-10-01T01:11:13.658662+00:00",
@@ -26397,8 +26399,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gpt_oss|none": {
"attributableFailureCount": 0,
@@ -27402,15 +27404,15 @@
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-10-07T20:46:38.448824+00:00",
@@ -27423,7 +27425,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": {
@@ -41030,14 +41032,14 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none|30": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 30,
@@ -41050,7 +41052,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors|33": {
@@ -58998,20 +59000,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17438,
"totalRecords": 17820,
"terminalRecords": 17439,
"totalRecords": 17821,
"totals": {
"attributableFailureCount": 6262,
"attributableFailureCount": 6263,
"decisionFailureRate": 0.8648,
"decisionSuccessRate": 0.1352,
"decisionTotal": 7241,
"decisionTotal": 7242,
"failureBreakdown": {
"ambiguous_runtime": 4581,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 130,
"context_length": 327,
"framework_architecture_unsupported": 2280,
"framework_architecture_unsupported": 2281,
"memory_capacity": 1206,
"model_load": 571,
"platform_infrastructure": 955,
@@ -59022,14 +59024,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16459,
"failureCount": 16460,
"failureRate": 0.9439,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 955,
"successCount": 979,
"successRate": 0.0561,
"total": 17438,
"total": 17439,
"unresolvedFailureCount": 9242
},
"warnings": [
@@ -59039,14 +59041,14 @@
"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 Cambricon_mlu-370-x8 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-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU 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。",
@@ -59092,6 +59094,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17820,
"summarizedRecords": 17821,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -111,6 +111,7 @@
{"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": "2026-10-07T15:52:48.873111+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "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": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:16:38.547857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006761", "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": "2026-10-07T13:29:11.757302+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "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": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:12:49.394711+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006730", "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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T20:46:38.448824+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:52:49.757664+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006516", "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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T23:36:57.259705+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-21T19:52:49.751148+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006518", "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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T20:46:38.448855+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-21T19:52:49.749531+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006512", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "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": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "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": null, "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", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+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": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-22T08:17:47.558862+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:49:55.866013+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998525", "taskType": "text-generation", "verifyResult": -1}
{"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-patch-tokenizer", "lastSyncTime": "2026-09-24T13:31:51.262642+00:00", "modelId": "neuralmagic/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673858, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "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": 7860673858}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:46:02.415434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998415", "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-patch-tokenizer", "lastSyncTime": "2026-09-22T22:37:24.242959+00:00", "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:45:53.481324+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4998407", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-30T15:29:22.559055+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:41:35.705044+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998344", "taskType": "text-generation", "verifyResult": -1}

1084
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1954
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff