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

state: generation 11228 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 05:48:31 +00:00
parent f022bae88e
commit e4287fae84
9 changed files with 1867 additions and 1867 deletions
Download Patch File Download Diff File Expand all files Collapse all files

129
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T05:42:03.917217+00:00",
"lastSyncTime": "2026-09-21T05:42:03.443622+00:00",
"generatedAt": "2026-09-21T05:48:19.649042+00:00",
"lastSyncTime": "2026-09-21T05:48:19.353127+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3040,23 +3040,23 @@
"decisionSuccessRate": 0.2679,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 28,
"model_load": 11,
"tokenizer_compatibility": 2
},
"failureCount": 49,
"failureRate": 0.7656,
"failureCount": 50,
"failureRate": 0.7692,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2344,
"successRate": 0.2308,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 64,
"unresolvedFailureCount": 8
"total": 65,
"unresolvedFailureCount": 9
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -5231,7 +5231,7 @@
"decisionSuccessRate": 0.0236,
"decisionTotal": 3601,
"failureBreakdown": {
"ambiguous_runtime": 1469,
"ambiguous_runtime": 1470,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5245,15 +5245,15 @@
"tokenizer_compatibility": 410,
"参数/模板问题": 41
},
"failureCount": 5891,
"failureCount": 5892,
"failureRate": 0.9858,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 85,
"successRate": 0.0142,
"total": 5976,
"unresolvedFailureCount": 1510
"total": 5977,
"unresolvedFailureCount": 1511
},
"vllm-customized": {
"attributableFailureCount": 3,
@@ -5393,7 +5393,7 @@
"unresolvedFailureCount": 67
}
},
"generatedAt": "2026-09-21T05:42:03.905867+00:00",
"generatedAt": "2026-09-21T05:48:19.638018+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5455,7 +5455,7 @@
"decisionSuccessRate": 0.1214,
"decisionTotal": 206,
"failureBreakdown": {
"ambiguous_runtime": 138,
"ambiguous_runtime": 139,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 116,
@@ -5469,15 +5469,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 624,
"failureCount": 625,
"failureRate": 0.9615,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0385,
"total": 649,
"unresolvedFailureCount": 441
"total": 650,
"unresolvedFailureCount": 442
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 713,
@@ -7444,9 +7444,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"model_load": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "phi3",
@@ -7458,8 +7459,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|plamo3|none": {
"attributableFailureCount": 1,
@@ -14935,13 +14936,13 @@
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 2,
"model_load": 4,
"tokenizer_compatibility": 1
},
"failureCount": 14,
"failureRate": 0.9333,
"failureCount": 15,
"failureRate": 0.9375,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T05:07:16.468545+00:00",
@@ -14949,11 +14950,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0667,
"successRate": 0.0625,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 7
"total": 16,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 1,
@@ -15632,31 +15633,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T16:44:23.353819+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -16268,9 +16244,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"model_load": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T05:07:16.468553+00:00",
@@ -16283,8 +16260,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -21708,6 +21685,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|phi3|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|plamo3|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -32256,15 +32257,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16152,
"totalRecords": 16333,
"terminalRecords": 16153,
"totalRecords": 16334,
"totals": {
"attributableFailureCount": 5854,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6795,
"failureBreakdown": {
"ambiguous_runtime": 3880,
"ambiguous_runtime": 3881,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -32280,31 +32281,31 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15211,
"failureCount": 15212,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 923,
"successCount": 941,
"successRate": 0.0583,
"total": 16152,
"unresolvedFailureCount": 8434
"total": 16153,
"unresolvedFailureCount": 8435
},
"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 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。",
"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。",
@@ -32343,6 +32344,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16333,
"summarizedRecords": 16334,
"version": 1
}