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

state: generation 19043 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-01 03:13:29 +00:00
parent 661573ea7b
commit cba22d8611
8 changed files with 2153 additions and 1811 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": "2026-10-01T03:00:54.727019+00:00",
"lastSyncTime": "2026-10-01T03:00:54.465128+00:00",
"generatedAt": "2026-10-01T03:09:40.906759+00:00",
"lastSyncTime": "2026-10-01T03:09:40.644809+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4050,24 +4050,24 @@
"decisionSuccessRate": 0.4815,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 49,
"ambiguous_runtime": 50,
"framework_architecture_unsupported": 11,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 66,
"failureRate": 0.8354,
"failureCount": 67,
"failureRate": 0.8375,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1646,
"successRate": 0.1625,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 79,
"unresolvedFailureCount": 52
"total": 80,
"unresolvedFailureCount": 53
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 22,
@@ -6098,7 +6098,7 @@
"decisionSuccessRate": 0.4074,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 93,
"ambiguous_runtime": 94,
"framework_architecture_unsupported": 26,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6106,15 +6106,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 133,
"failureRate": 0.8581,
"failureCount": 134,
"failureRate": 0.859,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1419,
"total": 155,
"unresolvedFailureCount": 100
"successRate": 0.141,
"total": 156,
"unresolvedFailureCount": 101
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 58,
@@ -6217,7 +6217,7 @@
"unresolvedFailureCount": 220
}
},
"generatedAt": "2026-10-01T03:00:54.712873+00:00",
"generatedAt": "2026-10-01T03:09:40.892872+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 112,
@@ -6339,7 +6339,7 @@
"decisionSuccessRate": 0.2,
"decisionTotal": 75,
"failureBreakdown": {
"ambiguous_runtime": 153,
"ambiguous_runtime": 154,
"framework_architecture_unsupported": 48,
"memory_capacity": 4,
"model_load": 5,
@@ -6348,15 +6348,15 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 278,
"failureRate": 0.9488,
"failureCount": 279,
"failureRate": 0.949,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0512,
"total": 293,
"unresolvedFailureCount": 216
"successRate": 0.051,
"total": 294,
"unresolvedFailureCount": 217
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -13653,6 +13653,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|torchao": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"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": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38942,6 +38965,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|torchao|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": "torchao",
"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,
@@ -54119,15 +54166,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17183,
"totalRecords": 17404,
"terminalRecords": 17184,
"totalRecords": 17405,
"totals": {
"attributableFailureCount": 6161,
"decisionFailureRate": 0.8634,
"decisionSuccessRate": 0.1366,
"decisionTotal": 7136,
"failureBreakdown": {
"ambiguous_runtime": 4480,
"ambiguous_runtime": 4481,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -54143,30 +54190,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16208,
"failureCount": 16209,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 944,
"successCount": 975,
"successRate": 0.0567,
"total": 17183,
"unresolvedFailureCount": 9103
"total": 17184,
"unresolvedFailureCount": 9104
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 Cambricon_mlu-370-x4 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 hygon_k100-ai 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 Mthreads_s4000 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 Vastai_va16 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。",
"GPU MetaX_c-500 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"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 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。",
@@ -54211,6 +54258,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17404,
"summarizedRecords": 17405,
"version": 1
}