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

state: generation 5693 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-11 12:52:37 +00:00
parent 19ac7409f6
commit 79ee103fe8
9 changed files with 2352 additions and 2354 deletions
Download Patch File Download Diff File Expand all files Collapse all files

114
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T11:19:08.559808+00:00",
"lastSyncTime": "2026-09-11T11:19:08.306651+00:00",
"generatedAt": "2026-09-11T12:50:33.981130+00:00",
"lastSyncTime": "2026-09-11T12:50:33.752023+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 81,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 91,
"attributableFailureCount": 82,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 32,
"model_load": 33,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 149,
"failureRate": 0.9371,
"failureCount": 150,
"failureRate": 0.9375,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0629,
"successRate": 0.0625,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 159,
"total": 160,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 135,
"decisionFailureRate": 0.7377,
"decisionSuccessRate": 0.2623,
"decisionTotal": 183,
"attributableFailureCount": 136,
"decisionFailureRate": 0.7391,
"decisionSuccessRate": 0.2609,
"decisionTotal": 184,
"failureBreakdown": {
"ambiguous_runtime": 128,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 34,
"model_load": 35,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 994,
"failureRate": 0.9539,
"failureCount": 995,
"failureRate": 0.954,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0461,
"total": 1042,
"successRate": 0.046,
"total": 1043,
"unresolvedFailureCount": 858
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T11:19:08.555805+00:00",
"generatedAt": "2026-09-11T12:50:33.976285+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 81,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 91,
"attributableFailureCount": 82,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 32,
"model_load": 33,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 149,
"failureRate": 0.9371,
"failureCount": 150,
"failureRate": 0.9375,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0629,
"total": 159,
"successRate": 0.0625,
"total": 160,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4210,18 +4210,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 3,
"backend_operator": 2,
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4233,27 +4233,27 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"total": 6,
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 14,
"consecutiveFailures": 15,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 6,
"model_load": 11,
"framework_architecture_unsupported": 5,
"model_load": 12,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T07:33:47.206168+00:00",
"lastTerminalAt": "2026-09-11T12:50:33.752023+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -6938,19 +6938,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1653,
"totalRecords": 1740,
"terminalRecords": 1654,
"totalRecords": 1741,
"totals": {
"attributableFailureCount": 433,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 486,
"attributableFailureCount": 434,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 487,
"failureBreakdown": {
"ambiguous_runtime": 391,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 56,
"model_load": 57,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6958,30 +6958,31 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1600,
"failureRate": 0.9679,
"failureCount": 1601,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0321,
"total": 1653,
"successRate": 0.032,
"total": 1654,
"unresolvedFailureCount": 1163
},
"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。",
@@ -6996,11 +6997,10 @@
"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": 1740,
"summarizedRecords": 1741,
"version": 1
}