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

state: generation 11670 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 19:52:49 +00:00
parent 80689bb05e
commit a6ab208d88
7 changed files with 104 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T19:49:38.160009+00:00",
"lastSyncTime": "2026-09-21T19:49:37.657161+00:00",
"generatedAt": "2026-09-21T19:52:34.453108+00:00",
"lastSyncTime": "2026-09-21T19:52:34.157602+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3347,16 +3347,16 @@
"unresolvedFailureCount": 20
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3366,7 +3366,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|unknown|feature_emb": {
@@ -5421,17 +5421,17 @@
"unresolvedFailureCount": 6446
},
"vllm": {
"attributableFailureCount": 3541,
"attributableFailureCount": 3542,
"decisionFailureRate": 0.9758,
"decisionSuccessRate": 0.0242,
"decisionTotal": 3629,
"decisionTotal": 3630,
"failureBreakdown": {
"ambiguous_runtime": 1497,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1308,
"framework_architecture_unsupported": 1309,
"memory_capacity": 722,
"model_load": 207,
"platform_infrastructure": 865,
@@ -5440,14 +5440,14 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5949,
"failureCount": 5950,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6037,
"total": 6038,
"unresolvedFailureCount": 1543
},
"vllm-customized": {
@@ -5594,7 +5594,7 @@
"unresolvedFailureCount": 107
}
},
"generatedAt": "2026-09-21T19:49:38.148216+00:00",
"generatedAt": "2026-09-21T19:52:34.442165+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5681,15 +5681,15 @@
"unresolvedFailureCount": 483
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 716,
"decisionFailureRate": 0.9075,
"decisionSuccessRate": 0.0925,
"decisionTotal": 789,
"attributableFailureCount": 717,
"decisionFailureRate": 0.9076,
"decisionSuccessRate": 0.0924,
"decisionTotal": 790,
"failureBreakdown": {
"ambiguous_runtime": 435,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 272,
"framework_architecture_unsupported": 273,
"memory_capacity": 218,
"model_load": 5,
"platform_infrastructure": 15,
@@ -5699,14 +5699,14 @@
"日志缺失": 13,
"验证失败": 40
},
"failureCount": 1505,
"failureRate": 0.9537,
"failureCount": 1506,
"failureRate": 0.9538,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 73,
"successRate": 0.0463,
"total": 1578,
"successRate": 0.0462,
"total": 1579,
"unresolvedFailureCount": 774
},
"Cambricon_mlu-370-x8": {
@@ -9548,6 +9548,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "spark2_5",
"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": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -26457,6 +26480,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "spark2_5",
"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": 0
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -37590,20 +37637,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16387,
"totalRecords": 16581,
"terminalRecords": 16388,
"totalRecords": 16582,
"totals": {
"attributableFailureCount": 5908,
"attributableFailureCount": 5909,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6854,
"decisionTotal": 6855,
"failureBreakdown": {
"ambiguous_runtime": 4024,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
"context_length": 321,
"framework_architecture_unsupported": 2086,
"framework_architecture_unsupported": 2087,
"memory_capacity": 1199,
"model_load": 499,
"platform_infrastructure": 925,
@@ -37614,31 +37661,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15441,
"failureCount": 15442,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0577,
"total": 16387,
"total": 16388,
"unresolvedFailureCount": 8608
},
"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。",
@@ -37678,6 +37725,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16581,
"summarizedRecords": 16582,
"version": 1
}