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

state: generation 4902 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 02:16:37 +00:00
parent e4900b8be7
commit 19fe9f7497
10 changed files with 1996 additions and 1998 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1306,7 +1306,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T02:14:06.326056+00:00",
"generatedAt": "2026-09-10T02:16:36.827241+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 348,
"listingErrors": 349,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T02:14:06.302712+00:00",
"updatedAt": "2026-09-10T02:16:36.802607+00:00",
"version": 1
}

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T02:12:31.935078+00:00",
"generatedAt": "2026-09-10T02:15:13.431523+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1516
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

74
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T01:59:31.455432+00:00",
"lastSyncTime": "2026-09-10T01:59:31.241099+00:00",
"generatedAt": "2026-09-10T02:15:07.319652+00:00",
"lastSyncTime": "2026-09-10T02:15:07.106881+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1540,24 +1540,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 73,
"failureRate": 0.9733,
"failureCount": 74,
"failureRate": 0.9737,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0267,
"successRate": 0.0263,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 75,
"unresolvedFailureCount": 53
"total": 76,
"unresolvedFailureCount": 54
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2289,7 +2289,7 @@
"decisionSuccessRate": 0.2883,
"decisionTotal": 163,
"failureBreakdown": {
"ambiguous_runtime": 98,
"ambiguous_runtime": 99,
"backend_operator": 2,
"framework_architecture_unsupported": 83,
"memory_capacity": 5,
@@ -2298,15 +2298,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 943,
"failureRate": 0.9525,
"failureCount": 944,
"failureRate": 0.9526,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 47,
"successRate": 0.0475,
"total": 990,
"unresolvedFailureCount": 827
"successRate": 0.0474,
"total": 991,
"unresolvedFailureCount": 828
},
"vllm": {
"attributableFailureCount": 227,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T01:59:31.450803+00:00",
"generatedAt": "2026-09-10T02:15:07.315789+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2516,21 +2516,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 73,
"failureRate": 0.9733,
"failureCount": 74,
"failureRate": 0.9737,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0267,
"total": 75,
"unresolvedFailureCount": 53
"successRate": 0.0263,
"total": 76,
"unresolvedFailureCount": 54
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -4044,24 +4044,24 @@
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 1
},
"failureCount": 5,
"failureRate": 0.7143,
"failureCount": 6,
"failureRate": 0.75,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T10:14:08.904917+00:00",
"lastTerminalAt": "2026-09-10T02:15:07.106855+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.2857,
"successRate": 0.25,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 1
"total": 8,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 4,
@@ -6765,15 +6765,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1480,
"totalRecords": 1564,
"terminalRecords": 1481,
"totalRecords": 1565,
"totals": {
"attributableFailureCount": 390,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 438,
"failureBreakdown": {
"ambiguous_runtime": 273,
"ambiguous_runtime": 274,
"backend_operator": 25,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
@@ -6785,21 +6785,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1432,
"failureCount": 1433,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0324,
"total": 1480,
"unresolvedFailureCount": 1040
"total": 1481,
"unresolvedFailureCount": 1041
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 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。",
@@ -6807,7 +6807,7 @@
"GPU hygon_k100-ai 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 Sunrise_pt-200-x1 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。",
"组合 Iluvatar_mrv-100|unknown|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|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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6828,6 +6828,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1564,
"summarizedRecords": 1565,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,3 +1,4 @@
{"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": "", "lastSyncTime": "2026-09-10T02:15:07.106855+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497062", "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": "", "lastSyncTime": "2026-09-10T01:59:31.241099+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481728", "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": "", "lastSyncTime": "2026-09-10T01:59:31.241082+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:53:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481717", "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": "", "lastSyncTime": "2026-09-10T01:50:54.936003+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481654", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-07T05:45:22.903457+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080310", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012360+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:21:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459779", "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": "2026-09-07T05:18:43.228874+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-1.5B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:13:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080836", "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": ["mellum"], "framework": "", "lastSyncTime": "2026-09-07T05:18:43.228836+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4152438", "taskType": "text-generation", "verifyResult": -1}

1286
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1082
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff