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

state: generation 18518 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-29 19:47:43 +00:00
parent b5722606df
commit b9a75c9c8f
8 changed files with 1448 additions and 1425 deletions
Download Patch File Download Diff File Expand all files Collapse all files

92
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-29T18:58:11.626640+00:00",
"lastSyncTime": "2026-09-29T18:58:11.344500+00:00",
"generatedAt": "2026-09-29T19:45:24.021972+00:00",
"lastSyncTime": "2026-09-29T19:45:23.746619+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4007,24 +4007,24 @@
"decisionSuccessRate": 0.4815,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 48,
"ambiguous_runtime": 49,
"framework_architecture_unsupported": 11,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 65,
"failureRate": 0.8333,
"failureCount": 66,
"failureRate": 0.8354,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1667,
"successRate": 0.1646,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 78,
"unresolvedFailureCount": 51
"total": 79,
"unresolvedFailureCount": 52
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 22,
@@ -6054,7 +6054,7 @@
"decisionSuccessRate": 0.4118,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 91,
"ambiguous_runtime": 92,
"framework_architecture_unsupported": 24,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6062,15 +6062,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 129,
"failureRate": 0.86,
"failureCount": 130,
"failureRate": 0.8609,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 21,
"successRate": 0.14,
"total": 150,
"unresolvedFailureCount": 98
"successRate": 0.1391,
"total": 151,
"unresolvedFailureCount": 99
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 56,
@@ -6173,7 +6173,7 @@
"unresolvedFailureCount": 205
}
},
"generatedAt": "2026-09-29T18:58:11.612344+00:00",
"generatedAt": "2026-09-29T19:45:24.009437+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 105,
@@ -6294,7 +6294,7 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 75,
"failureBreakdown": {
"ambiguous_runtime": 152,
"ambiguous_runtime": 153,
"framework_architecture_unsupported": 48,
"memory_capacity": 4,
"model_load": 5,
@@ -6303,15 +6303,15 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 277,
"failureRate": 0.9486,
"failureCount": 278,
"failureRate": 0.9488,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0514,
"total": 292,
"unresolvedFailureCount": 215
"successRate": 0.0512,
"total": 293,
"unresolvedFailureCount": 216
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -13384,9 +13384,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
@@ -13398,8 +13398,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -38046,6 +38046,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -53008,15 +53032,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17131,
"totalRecords": 17352,
"terminalRecords": 17132,
"totalRecords": 17353,
"totals": {
"attributableFailureCount": 6138,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7110,
"failureBreakdown": {
"ambiguous_runtime": 4456,
"ambiguous_runtime": 4457,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -53032,15 +53056,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16159,
"failureCount": 16160,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 942,
"successCount": 972,
"successRate": 0.0567,
"total": 17131,
"unresolvedFailureCount": 9079
"total": 17132,
"unresolvedFailureCount": 9080
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -53069,7 +53093,6 @@
"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 Cambricon_mlu-370-x4|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -53095,10 +53118,11 @@
"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": 17352,
"summarizedRecords": 17353,
"version": 1
}