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

state: generation 4987 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 05:51:31 +00:00
parent 15a2633657
commit a153f9f452
9 changed files with 2148 additions and 2151 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T05:27:18.664485+00:00",
"lastSyncTime": "2026-09-10T05:27:18.447582+00:00",
"generatedAt": "2026-09-10T05:49:48.836041+00:00",
"lastSyncTime": "2026-09-10T05:49:48.500487+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1484,13 +1484,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 25,
"ambiguous_runtime": 27,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 62,
"failureCount": 64,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1500,8 +1500,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 62,
"unresolvedFailureCount": 25
"total": 64,
"unresolvedFailureCount": 27
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 24,
@@ -2331,7 +2331,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 138,
"ambiguous_runtime": 140,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2342,15 +2342,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 390,
"failureCount": 392,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 390,
"unresolvedFailureCount": 159
"total": 392,
"unresolvedFailureCount": 161
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2453,7 +2453,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T05:27:18.659030+00:00",
"generatedAt": "2026-09-10T05:49:48.831661+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2484,7 +2484,7 @@
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 26,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 1,
@@ -2493,15 +2493,15 @@
"参数/模板问题": 11,
"验证失败": 175
},
"failureCount": 250,
"failureCount": 252,
"failureRate": 0.9921,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0079,
"total": 252,
"unresolvedFailureCount": 212
"total": 254,
"unresolvedFailureCount": 214
},
"Biren_166m": {
"attributableFailureCount": 25,
@@ -4000,21 +4000,21 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 9
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 7
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T04:27:58.701433+00:00",
"lastTerminalAt": "2026-09-10T05:49:48.500487+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4023,7 +4023,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 11
"unresolvedFailureCount": 13
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4414,21 +4414,20 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"model_load": 2,
"repository_structure": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 12,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4440,7 +4439,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 12,
"total": 10,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -6880,15 +6879,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1508,
"totalRecords": 1595,
"terminalRecords": 1510,
"totalRecords": 1597,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 289,
"ambiguous_runtime": 291,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6900,21 +6899,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1459,
"failureCount": 1461,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0325,
"total": 1508,
"unresolvedFailureCount": 1057
"total": 1510,
"unresolvedFailureCount": 1059
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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。",
"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。",
@@ -6922,7 +6921,7 @@
"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 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 Iluvatar_bi-150 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-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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6943,6 +6942,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1595,
"summarizedRecords": 1597,
"version": 1
}