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

state: generation 18434 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-29 15:29:19 +00:00
parent aa36130523
commit cfebd1c467
8 changed files with 1681 additions and 1593 deletions
Download Patch File Download Diff File Expand all files Collapse all files

202
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-29T13:18:15.837463+00:00",
"lastSyncTime": "2026-09-29T13:18:15.544758+00:00",
"generatedAt": "2026-09-29T15:27:45.827363+00:00",
"lastSyncTime": "2026-09-29T15:27:45.443270+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4548,30 +4548,30 @@
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 41,
"decisionFailureRate": 0.6833,
"decisionSuccessRate": 0.3167,
"decisionTotal": 60,
"attributableFailureCount": 42,
"decisionFailureRate": 0.6885,
"decisionSuccessRate": 0.3115,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 24,
"backend_operator": 6,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 67,
"failureRate": 0.7791,
"failureCount": 68,
"failureRate": 0.7816,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.2209,
"successRate": 0.2184,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 86,
"total": 87,
"unresolvedFailureCount": 26
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -5616,23 +5616,23 @@
"decisionSuccessRate": 0.1515,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 25,
"ambiguous_runtime": 26,
"framework_architecture_unsupported": 19,
"model_load": 9,
"参数/模板问题": 4
},
"failureCount": 57,
"failureRate": 0.9194,
"failureCount": 58,
"failureRate": 0.9206,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.0806,
"successRate": 0.0794,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 62,
"unresolvedFailureCount": 29
"total": 63,
"unresolvedFailureCount": 30
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 430,
@@ -6076,27 +6076,27 @@
"unresolvedFailureCount": 53
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 41,
"decisionFailureRate": 0.6833,
"decisionSuccessRate": 0.3167,
"decisionTotal": 60,
"attributableFailureCount": 42,
"decisionFailureRate": 0.6885,
"decisionSuccessRate": 0.3115,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 24,
"backend_operator": 6,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 67,
"failureRate": 0.7791,
"failureCount": 68,
"failureRate": 0.7816,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.2209,
"total": 86,
"successRate": 0.2184,
"total": 87,
"unresolvedFailureCount": 26
},
"vllm_fix_tokenizer": {
@@ -6105,7 +6105,7 @@
"decisionSuccessRate": 0.0312,
"decisionTotal": 160,
"failureBreakdown": {
"ambiguous_runtime": 327,
"ambiguous_runtime": 328,
"backend_operator": 9,
"framework_architecture_unsupported": 36,
"memory_capacity": 10,
@@ -6114,15 +6114,15 @@
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 517,
"failureCount": 518,
"failureRate": 0.9904,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0096,
"total": 522,
"unresolvedFailureCount": 340
"total": 523,
"unresolvedFailureCount": 341
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 130,
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 199
}
},
"generatedAt": "2026-09-29T13:18:15.824122+00:00",
"generatedAt": "2026-09-29T15:27:45.813485+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 103,
@@ -6317,16 +6317,16 @@
"unresolvedFailureCount": 568
},
"Iluvatar_bi-150": {
"attributableFailureCount": 758,
"decisionFailureRate": 0.8348,
"decisionSuccessRate": 0.1652,
"decisionTotal": 908,
"attributableFailureCount": 759,
"decisionFailureRate": 0.835,
"decisionSuccessRate": 0.165,
"decisionTotal": 909,
"failureBreakdown": {
"ambiguous_runtime": 651,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
"framework_architecture_unsupported": 251,
"framework_architecture_unsupported": 252,
"memory_capacity": 153,
"model_load": 126,
"platform_infrastructure": 21,
@@ -6337,14 +6337,14 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1935,
"failureCount": 1936,
"failureRate": 0.9281,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0719,
"total": 2085,
"total": 2086,
"unresolvedFailureCount": 1156
},
"Iluvatar_mrv-100": {
@@ -6522,7 +6522,7 @@
"decisionSuccessRate": 0.1103,
"decisionTotal": 517,
"failureBreakdown": {
"ambiguous_runtime": 825,
"ambiguous_runtime": 826,
"context_length": 9,
"framework_architecture_unsupported": 198,
"memory_capacity": 133,
@@ -6534,15 +6534,15 @@
"日志缺失": 124,
"验证失败": 130
},
"failureCount": 1795,
"failureCount": 1796,
"failureRate": 0.9692,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 57,
"successRate": 0.0308,
"total": 1852,
"unresolvedFailureCount": 1321
"total": 1853,
"unresolvedFailureCount": 1322
},
"hygon_k100-ai": {
"attributableFailureCount": 736,
@@ -15638,6 +15638,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -21739,6 +21762,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -40995,6 +41041,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -50440,6 +50510,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen2|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -52679,20 +52773,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17111,
"totalRecords": 17332,
"terminalRecords": 17113,
"totalRecords": 17334,
"totals": {
"attributableFailureCount": 6133,
"attributableFailureCount": 6134,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7104,
"decisionTotal": 7105,
"failureBreakdown": {
"ambiguous_runtime": 4442,
"ambiguous_runtime": 4443,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2187,
"framework_architecture_unsupported": 2188,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 942,
@@ -52703,15 +52797,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16140,
"failureCount": 16142,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 942,
"successCount": 971,
"successRate": 0.0567,
"total": 17111,
"unresolvedFailureCount": 9065
"total": 17113,
"unresolvedFailureCount": 9066
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -52740,7 +52834,6 @@
"组合 Kunlunxin_p-800|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 Ascend_910-b4|llamacpp|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|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 Kunlunxin_p-800|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 MetaX_c-500|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 Ascend_910-b4|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_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -52765,10 +52858,11 @@
"组合 hygon_k100-ai|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 Cambricon_mlu-370-x4|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 Ascend_910-b3|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 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 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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17332,
"summarizedRecords": 17334,
"version": 1
}