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

state: generation 5699 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-11 13:11:39 +00:00
parent 6c88d28b96
commit f52cf7ad5c
9 changed files with 2163 additions and 2165 deletions
Download Patch File Download Diff File Expand all files Collapse all files

106
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T12:59:52.891244+00:00",
"lastSyncTime": "2026-09-11T12:59:52.253401+00:00",
"generatedAt": "2026-09-11T13:09:08.434430+00:00",
"lastSyncTime": "2026-09-11T13:09:08.149747+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 82,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 92,
"attributableFailureCount": 83,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 93,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 33,
"model_load": 34,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 150,
"failureRate": 0.9375,
"failureCount": 151,
"failureRate": 0.9379,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0625,
"successRate": 0.0621,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 160,
"total": 161,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 136,
"decisionFailureRate": 0.7391,
"decisionSuccessRate": 0.2609,
"decisionTotal": 184,
"attributableFailureCount": 137,
"decisionFailureRate": 0.7405,
"decisionSuccessRate": 0.2595,
"decisionTotal": 185,
"failureBreakdown": {
"ambiguous_runtime": 129,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 35,
"model_load": 36,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 996,
"failureRate": 0.954,
"failureCount": 997,
"failureRate": 0.9541,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.046,
"total": 1044,
"successRate": 0.0459,
"total": 1045,
"unresolvedFailureCount": 859
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T12:59:52.887160+00:00",
"generatedAt": "2026-09-11T13:09:08.430453+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 82,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 92,
"attributableFailureCount": 83,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 93,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 33,
"model_load": 34,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 150,
"failureRate": 0.9375,
"failureCount": 151,
"failureRate": 0.9379,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0625,
"total": 160,
"successRate": 0.0621,
"total": 161,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4237,7 +4237,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 15,
"consecutiveFailures": 16,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
@@ -4252,7 +4252,7 @@
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T12:50:33.752023+00:00",
"lastTerminalAt": "2026-09-11T13:09:08.149747+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4570,19 +4570,19 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 3,
"repository_structure": 1,
"runtime_memory": 1
},
"failureCount": 18,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4594,7 +4594,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 18,
"total": 17,
"unresolvedFailureCount": 12
}
},
@@ -6937,19 +6937,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1655,
"totalRecords": 1742,
"terminalRecords": 1656,
"totalRecords": 1743,
"totals": {
"attributableFailureCount": 434,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 487,
"attributableFailureCount": 435,
"decisionFailureRate": 0.8914,
"decisionSuccessRate": 0.1086,
"decisionTotal": 488,
"failureBreakdown": {
"ambiguous_runtime": 392,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 57,
"model_load": 58,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6957,30 +6957,31 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1602,
"failureCount": 1603,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.032,
"total": 1655,
"total": 1656,
"unresolvedFailureCount": 1164
},
"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。",
@@ -6995,11 +6996,10 @@
"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": 1742,
"summarizedRecords": 1743,
"version": 1
}