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

state: generation 9850 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-19 14:26:46 +00:00
parent 280ee4eb0c
commit 7cd7646268
9 changed files with 1868 additions and 1823 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1764,7 +1764,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-19T14:24:23.273453+00:00",
"generatedAt": "2026-09-19T14:26:46.418798+00:00",
"summary": {
"activeBlockCount": 85,
"byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 718,
"listingErrors": 719,
"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": "2026-09-19T14:24:23.249290+00:00",
"updatedAt": "2026-09-19T14:26:46.395172+00:00",
"version": 1
}

2
.modelhub_state/market_intelligence.json
View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-19T14:23:07.025869+00:00",
"generatedAt": "2026-09-19T14:25:30.118523+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

175
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T14:10:52.788588+00:00",
"lastSyncTime": "2026-09-19T14:10:52.522734+00:00",
"generatedAt": "2026-09-19T14:25:24.291714+00:00",
"lastSyncTime": "2026-09-19T14:25:23.989355+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2655,26 +2655,26 @@
"unresolvedFailureCount": 145
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 5,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 6,
"attributableFailureCount": 6,
"decisionFailureRate": 0.8571,
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 5,
"model_load": 1
},
"failureCount": 13,
"failureRate": 0.9286,
"failureCount": 14,
"failureRate": 0.9333,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0714,
"successRate": 0.0667,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 8
},
"Vastai_va16|vllm|text-generation": {
@@ -2750,13 +2750,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 10,
"model_load": 1,
"runtime_memory": 5,
"参数/模板问题": 8
},
"failureCount": 34,
"failureCount": 35,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -2766,8 +2766,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 18
"total": 35,
"unresolvedFailureCount": 19
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 56,
@@ -2915,21 +2915,21 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 10,
"model_load": 1,
"runtime_memory": 5,
"参数/模板问题": 8
},
"failureCount": 34,
"failureCount": 35,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 34,
"unresolvedFailureCount": 18
"total": 35,
"unresolvedFailureCount": 19
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 28,
@@ -2955,27 +2955,27 @@
"unresolvedFailureCount": 14
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 67,
"decisionFailureRate": 0.9853,
"decisionSuccessRate": 0.0147,
"decisionTotal": 68,
"attributableFailureCount": 68,
"decisionFailureRate": 0.9855,
"decisionSuccessRate": 0.0145,
"decisionTotal": 69,
"failureBreakdown": {
"ambiguous_runtime": 83,
"backend_operator": 7,
"framework_architecture_unsupported": 11,
"framework_architecture_unsupported": 12,
"model_load": 1,
"platform_infrastructure": 8,
"tokenizer_compatibility": 48,
"参数/模板问题": 8
},
"failureCount": 166,
"failureCount": 167,
"failureRate": 0.994,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 8,
"successCount": 1,
"successRate": 0.006,
"total": 167,
"total": 168,
"unresolvedFailureCount": 91
},
"vllm_tokenizer_patch": {
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 20
}
},
"generatedAt": "2026-09-19T14:10:52.783219+00:00",
"generatedAt": "2026-09-19T14:25:24.286382+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3288,26 +3288,26 @@
"unresolvedFailureCount": 51
},
"Vastai_va16": {
"attributableFailureCount": 66,
"decisionFailureRate": 0.7765,
"decisionSuccessRate": 0.2235,
"decisionTotal": 85,
"attributableFailureCount": 67,
"decisionFailureRate": 0.7791,
"decisionSuccessRate": 0.2209,
"decisionTotal": 86,
"failureBreakdown": {
"ambiguous_runtime": 84,
"framework_architecture_unsupported": 59,
"framework_architecture_unsupported": 60,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 15,
"验证失败": 130
},
"failureCount": 295,
"failureRate": 0.9395,
"failureCount": 296,
"failureRate": 0.9397,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0605,
"total": 314,
"successRate": 0.0603,
"total": 315,
"unresolvedFailureCount": 229
},
"hygon_k100-ai": {
@@ -3316,7 +3316,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 72,
"failureBreakdown": {
"ambiguous_runtime": 37,
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 54,
"memory_capacity": 1,
"model_load": 6,
@@ -3325,15 +3325,15 @@
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 146,
"failureCount": 147,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 146,
"unresolvedFailureCount": 74
"total": 147,
"unresolvedFailureCount": 75
}
},
"observedGpuMemoryGiB": {
@@ -7574,6 +7574,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7696,11 +7719,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"ambiguous_runtime": 2,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "llama",
@@ -7712,8 +7735,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 1
"total": 4,
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 1,
@@ -15297,6 +15320,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -15472,10 +15519,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"ambiguous_runtime": 2,
"runtime_memory": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
@@ -15488,8 +15535,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors|32": {
"attributableFailureCount": 1,
@@ -15733,17 +15780,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2340,
"totalRecords": 2443,
"terminalRecords": 2342,
"totalRecords": 2445,
"totals": {
"attributableFailureCount": 764,
"decisionFailureRate": 0.8171,
"decisionSuccessRate": 0.1829,
"decisionTotal": 935,
"attributableFailureCount": 765,
"decisionFailureRate": 0.8173,
"decisionSuccessRate": 0.1827,
"decisionTotal": 936,
"failureBreakdown": {
"ambiguous_runtime": 588,
"ambiguous_runtime": 589,
"backend_operator": 55,
"framework_architecture_unsupported": 512,
"framework_architecture_unsupported": 513,
"memory_capacity": 12,
"model_load": 89,
"platform_infrastructure": 11,
@@ -15753,18 +15800,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2169,
"failureRate": 0.9269,
"failureCount": 2171,
"failureRate": 0.927,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 171,
"successRate": 0.0731,
"total": 2340,
"unresolvedFailureCount": 1394
"successRate": 0.073,
"total": 2342,
"unresolvedFailureCount": 1395
},
"warnings": [
"GPU Iluvatar_bi-150 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 Ascend_910-b3 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。",
@@ -15775,7 +15822,7 @@
"GPU Sunrise_pt-200-x1 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 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-150 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 MetaX_c-500|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-b4|vllm_tokenizer_patch|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|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -15800,6 +15847,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2443,
"summarizedRecords": 2445,
"version": 1
}

1002
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

976
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff