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

state: generation 11300 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 07:36:19 +00:00
parent 347ec0df7e
commit acb190b0fe
8 changed files with 1872 additions and 1824 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T07:18:01.667464+00:00",
"lastSyncTime": "2026-09-21T07:18:01.568496+00:00",
"generatedAt": "2026-09-21T07:36:10.361847+00:00",
"lastSyncTime": "2026-09-21T07:35:50.256608+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3156,20 +3156,21 @@
"failureBreakdown": {
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 6,
"model_load": 1
"model_load": 1,
"验证失败": 1
},
"failureCount": 22,
"failureRate": 0.7333,
"failureCount": 23,
"failureRate": 0.7419,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.2667,
"successRate": 0.2581,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 30,
"unresolvedFailureCount": 15
"total": 31,
"unresolvedFailureCount": 16
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -5298,17 +5299,18 @@
"framework_architecture_unsupported": 17,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
"参数/模板问题": 3,
"验证失败": 1
},
"failureCount": 74,
"failureRate": 0.7872,
"failureCount": 75,
"failureRate": 0.7895,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.2128,
"total": 94,
"unresolvedFailureCount": 54
"successRate": 0.2105,
"total": 95,
"unresolvedFailureCount": 55
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 27,
@@ -5407,7 +5409,7 @@
"unresolvedFailureCount": 67
}
},
"generatedAt": "2026-09-21T07:18:01.620340+00:00",
"generatedAt": "2026-09-21T07:36:10.351855+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5510,17 +5512,17 @@
"tokenizer_compatibility": 35,
"参数/模板问题": 284,
"日志缺失": 13,
"验证失败": 39
"验证失败": 40
},
"failureCount": 1496,
"failureCount": 1497,
"failureRate": 0.9535,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 73,
"successRate": 0.0465,
"total": 1569,
"unresolvedFailureCount": 767
"total": 1570,
"unresolvedFailureCount": 768
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 44,
@@ -8162,6 +8164,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|zaya|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"验证失败": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "zaya",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -22617,6 +22642,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|zaya|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"验证失败": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "zaya",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -32263,8 +32312,8 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16167,
"totalRecords": 16349,
"terminalRecords": 16168,
"totalRecords": 16350,
"totals": {
"attributableFailureCount": 5855,
"decisionFailureRate": 0.8614,
@@ -32285,33 +32334,33 @@
"tokenizer_compatibility": 659,
"参数/模板问题": 3171,
"日志缺失": 719,
"验证失败": 673
"验证失败": 674
},
"failureCount": 15225,
"failureCount": 15226,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 923,
"successCount": 942,
"successRate": 0.0583,
"total": 16167,
"unresolvedFailureCount": 8447
"total": 16168,
"unresolvedFailureCount": 8448
},
"warnings": [
"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 Cambricon_mlu-370-x8 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 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-100 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-b3 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 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。",
"组合 Iluvatar_bi-150|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|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|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -32350,6 +32399,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16349,
"summarizedRecords": 16350,
"version": 1
}