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

state: generation 6117 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 08:40:43 +00:00
parent 9d3cfed3ff
commit 89fbbdbe23
9 changed files with 2139 additions and 2141 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T08:20:40.395370+00:00",
"lastSyncTime": "2026-09-12T08:20:40.114700+00:00",
"generatedAt": "2026-09-12T08:38:57.450801+00:00",
"lastSyncTime": "2026-09-12T08:38:57.213433+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1845,30 +1845,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 88,
"decisionFailureRate": 0.8713,
"decisionSuccessRate": 0.1287,
"decisionTotal": 101,
"attributableFailureCount": 89,
"decisionFailureRate": 0.8725,
"decisionSuccessRate": 0.1275,
"decisionTotal": 102,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 38,
"model_load": 39,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 157,
"failureRate": 0.9235,
"failureCount": 158,
"failureRate": 0.924,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.0765,
"successRate": 0.076,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 170,
"total": 171,
"unresolvedFailureCount": 68
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -2370,29 +2370,29 @@
"unresolvedFailureCount": 7
},
"unknown": {
"attributableFailureCount": 143,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 195,
"attributableFailureCount": 144,
"decisionFailureRate": 0.7347,
"decisionSuccessRate": 0.2653,
"decisionTotal": 196,
"failureBreakdown": {
"ambiguous_runtime": 131,
"backend_operator": 4,
"framework_architecture_unsupported": 91,
"memory_capacity": 5,
"model_load": 40,
"model_load": 41,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1007,
"failureCount": 1008,
"failureRate": 0.9509,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 52,
"successRate": 0.0491,
"total": 1059,
"total": 1060,
"unresolvedFailureCount": 863
},
"vllm": {
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T08:20:40.389446+00:00",
"generatedAt": "2026-09-12T08:38:57.446440+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2688,27 +2688,27 @@
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 89,
"decisionFailureRate": 0.8725,
"decisionSuccessRate": 0.1275,
"decisionTotal": 102,
"attributableFailureCount": 90,
"decisionFailureRate": 0.8738,
"decisionSuccessRate": 0.1262,
"decisionTotal": 103,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 39,
"model_load": 40,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 158,
"failureRate": 0.924,
"failureCount": 159,
"failureRate": 0.9244,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 13,
"successRate": 0.076,
"total": 171,
"successRate": 0.0756,
"total": 172,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
@@ -4464,7 +4464,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 0,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
@@ -4478,7 +4478,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T08:20:40.114700+00:00",
"lastTerminalAt": "2026-09-12T08:38:57.213433+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7185,19 +7185,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1704,
"totalRecords": 1791,
"terminalRecords": 1705,
"totalRecords": 1792,
"totals": {
"attributableFailureCount": 470,
"decisionFailureRate": 0.8918,
"decisionSuccessRate": 0.1082,
"decisionTotal": 527,
"attributableFailureCount": 471,
"decisionFailureRate": 0.892,
"decisionSuccessRate": 0.108,
"decisionTotal": 528,
"failureBreakdown": {
"ambiguous_runtime": 399,
"backend_operator": 42,
"framework_architecture_unsupported": 288,
"memory_capacity": 11,
"model_load": 68,
"model_load": 69,
"platform_infrastructure": 4,
"repository_structure": 7,
"runtime_memory": 6,
@@ -7205,20 +7205,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1647,
"failureRate": 0.9665,
"failureCount": 1648,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0335,
"total": 1704,
"successRate": 0.0334,
"total": 1705,
"unresolvedFailureCount": 1173
},
"warnings": [
"GPU Ascend_910-b3 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 hygon_k100-ai 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7227,7 +7228,6 @@
"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-150 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。",
"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。",
"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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7249,6 +7249,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1791,
"summarizedRecords": 1792,
"version": 1
}