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

state: generation 8403 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-16 21:44:41 +00:00
parent baa529977a
commit 751c66984c
9 changed files with 1966 additions and 1897 deletions
Download Patch File Download Diff File Expand all files Collapse all files

165
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T21:33:41.248132+00:00",
"lastSyncTime": "2026-09-16T21:33:39.119052+00:00",
"generatedAt": "2026-09-16T21:42:45.309128+00:00",
"lastSyncTime": "2026-09-16T21:42:43.203719+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1948,25 +1948,25 @@
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 19,
"decisionFailureRate": 0.95,
"decisionSuccessRate": 0.05,
"decisionTotal": 20,
"attributableFailureCount": 21,
"decisionFailureRate": 0.9545,
"decisionSuccessRate": 0.0455,
"decisionTotal": 22,
"failureBreakdown": {
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 16,
"model_load": 5
},
"failureCount": 19,
"failureRate": 0.95,
"failureCount": 21,
"failureRate": 0.9545,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.05,
"successRate": 0.0455,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 20,
"total": 22,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2808,14 +2808,14 @@
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 377,
"decisionFailureRate": 0.9617,
"decisionSuccessRate": 0.0383,
"decisionTotal": 392,
"attributableFailureCount": 379,
"decisionFailureRate": 0.9619,
"decisionSuccessRate": 0.0381,
"decisionTotal": 394,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 281,
"framework_architecture_unsupported": 283,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2824,14 +2824,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 632,
"failureRate": 0.9768,
"failureCount": 634,
"failureRate": 0.9769,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0232,
"total": 647,
"successRate": 0.0231,
"total": 649,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2943,7 +2943,7 @@
"unresolvedFailureCount": 6
}
},
"generatedAt": "2026-09-16T21:33:41.242800+00:00",
"generatedAt": "2026-09-16T21:42:45.303114+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 51,
@@ -2994,14 +2994,14 @@
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 57,
"decisionFailureRate": 0.95,
"decisionSuccessRate": 0.05,
"decisionTotal": 60,
"attributableFailureCount": 59,
"decisionFailureRate": 0.9516,
"decisionSuccessRate": 0.0484,
"decisionTotal": 62,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 41,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 2,
@@ -3009,14 +3009,14 @@
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 116,
"failureRate": 0.9748,
"failureCount": 118,
"failureRate": 0.9752,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0252,
"total": 119,
"successRate": 0.0248,
"total": 121,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3549,6 +3549,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -3688,14 +3711,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
@@ -3707,7 +3730,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|rwkv7|none": {
@@ -7308,6 +7331,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7500,6 +7547,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11352,17 +11423,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2055,
"totalRecords": 2158,
"terminalRecords": 2057,
"totalRecords": 2160,
"totals": {
"attributableFailureCount": 667,
"decisionFailureRate": 0.8917,
"decisionSuccessRate": 0.1083,
"decisionTotal": 748,
"attributableFailureCount": 669,
"decisionFailureRate": 0.892,
"decisionSuccessRate": 0.108,
"decisionTotal": 750,
"failureBreakdown": {
"ambiguous_runtime": 500,
"backend_operator": 45,
"framework_architecture_unsupported": 439,
"framework_architecture_unsupported": 441,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -11372,14 +11443,14 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1974,
"failureCount": 1976,
"failureRate": 0.9606,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 81,
"successRate": 0.0394,
"total": 2055,
"total": 2057,
"unresolvedFailureCount": 1297
},
"warnings": [
@@ -11387,14 +11458,14 @@
"GPU Iluvatar_mrv-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-b4 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 Biren_166m 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 hygon_k100-ai 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 Ascend_910-b3 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 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 Biren_166m|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 Biren_166m|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_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -11419,6 +11490,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2158,
"summarizedRecords": 2160,
"version": 1
}