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

state: generation 5580 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-11 07:08:10 +00:00
parent 8343152c66
commit b56694cbcb
9 changed files with 3350 additions and 3349 deletions
Download Patch File Download Diff File Expand all files Collapse all files

98
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T05:08:00.294271+00:00",
"lastSyncTime": "2026-09-11T05:08:00.009961+00:00",
"generatedAt": "2026-09-11T07:05:27.225930+00:00",
"lastSyncTime": "2026-09-11T07:05:27.006934+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 78,
"decisionFailureRate": 0.8864,
"decisionSuccessRate": 0.1136,
"decisionTotal": 88,
"attributableFailureCount": 79,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 89,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 29,
"model_load": 30,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 146,
"failureRate": 0.9359,
"failureCount": 147,
"failureRate": 0.9363,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0641,
"successRate": 0.0637,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 156,
"total": 157,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2288,29 +2288,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 132,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 180,
"attributableFailureCount": 133,
"decisionFailureRate": 0.7348,
"decisionSuccessRate": 0.2652,
"decisionTotal": 181,
"failureBreakdown": {
"ambiguous_runtime": 128,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 31,
"model_load": 32,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 990,
"failureCount": 991,
"failureRate": 0.9538,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0462,
"total": 1038,
"total": 1039,
"unresolvedFailureCount": 857
},
"vllm": {
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T05:08:00.290509+00:00",
"generatedAt": "2026-09-11T07:05:27.222026+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2604,27 +2604,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 78,
"decisionFailureRate": 0.8864,
"decisionSuccessRate": 0.1136,
"decisionTotal": 88,
"attributableFailureCount": 79,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 89,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 29,
"model_load": 30,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 146,
"failureRate": 0.9359,
"failureCount": 147,
"failureRate": 0.9363,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0641,
"total": 156,
"successRate": 0.0637,
"total": 157,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4190,9 +4190,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 2
"参数/模板问题": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4204,8 +4204,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -4261,7 +4261,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 11,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
@@ -4276,7 +4276,7 @@
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T23:11:46.109095+00:00",
"lastTerminalAt": "2026-09-11T07:05:27.006934+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -6936,19 +6936,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1646,
"totalRecords": 1733,
"terminalRecords": 1647,
"totalRecords": 1734,
"totals": {
"attributableFailureCount": 427,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 480,
"attributableFailureCount": 428,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 481,
"failureBreakdown": {
"ambiguous_runtime": 391,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 53,
"model_load": 54,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6956,30 +6956,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1593,
"failureCount": 1594,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0322,
"total": 1646,
"total": 1647,
"unresolvedFailureCount": 1162
},
"warnings": [
"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 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 Mthreads_s4000 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 MetaX_c-500 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 Biren_166m 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 Iluvatar_bi-150 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 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x4|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 Mthreads_s4000|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 Cambricon_mlu-370-x8|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6994,11 +6995,10 @@
"组合 hygon_k100-ai|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 Iluvatar_bi-150|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|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-x4|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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1733,
"summarizedRecords": 1734,
"version": 1
}