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

state: generation 4908 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 02:34:21 +00:00
parent 6ad27345c4
commit 4c8bb192dc
11 changed files with 2123 additions and 2124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

124
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T02:23:37.333475+00:00",
"lastSyncTime": "2026-09-10T02:23:37.132500+00:00",
"generatedAt": "2026-09-10T02:32:07.743588+00:00",
"lastSyncTime": "2026-09-10T02:32:07.501704+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1379,12 +1379,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 41,
"failureCount": 42,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1394,8 +1394,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 41,
"unresolvedFailureCount": 15
"total": 42,
"unresolvedFailureCount": 16
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -1540,24 +1540,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 74,
"failureRate": 0.9737,
"failureCount": 75,
"failureRate": 0.974,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0263,
"successRate": 0.026,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 76,
"unresolvedFailureCount": 54
"total": 77,
"unresolvedFailureCount": 55
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2289,7 +2289,7 @@
"decisionSuccessRate": 0.2866,
"decisionTotal": 164,
"failureBreakdown": {
"ambiguous_runtime": 99,
"ambiguous_runtime": 100,
"backend_operator": 2,
"framework_architecture_unsupported": 84,
"memory_capacity": 5,
@@ -2298,15 +2298,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 945,
"failureRate": 0.9526,
"failureCount": 946,
"failureRate": 0.9527,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 47,
"successRate": 0.0474,
"total": 992,
"unresolvedFailureCount": 828
"successRate": 0.0473,
"total": 993,
"unresolvedFailureCount": 829
},
"vllm": {
"attributableFailureCount": 227,
@@ -2314,7 +2314,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 227,
"failureBreakdown": {
"ambiguous_runtime": 129,
"ambiguous_runtime": 130,
"backend_operator": 22,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
@@ -2325,15 +2325,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 378,
"failureCount": 379,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 378,
"unresolvedFailureCount": 150
"total": 379,
"unresolvedFailureCount": 151
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T02:23:37.327574+00:00",
"generatedAt": "2026-09-10T02:32:07.739281+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2444,22 +2444,22 @@
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 76,
"failureRate": 0.987,
"failureCount": 77,
"failureRate": 0.9872,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.013,
"total": 77,
"unresolvedFailureCount": 50
"successRate": 0.0128,
"total": 78,
"unresolvedFailureCount": 51
},
"Ascend_910-b4": {
"attributableFailureCount": 38,
@@ -2516,21 +2516,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 74,
"failureRate": 0.9737,
"failureCount": 75,
"failureRate": 0.974,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0263,
"total": 76,
"unresolvedFailureCount": 54
"successRate": 0.026,
"total": 77,
"unresolvedFailureCount": 55
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -3939,14 +3939,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 3
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T01:16:26.008857+00:00",
"lastTerminalAt": "2026-09-10T02:32:07.501688+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -3954,8 +3954,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 10
"total": 14,
"unresolvedFailureCount": 11
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -4044,24 +4044,24 @@
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 1
},
"failureCount": 6,
"failureRate": 0.75,
"failureCount": 7,
"failureRate": 0.7778,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:15:07.106855+00:00",
"lastTerminalAt": "2026-09-10T02:32:07.501704+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.25,
"successRate": 0.2222,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 2
"total": 9,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 4,
@@ -4634,12 +4634,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4651,8 +4651,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 7
"total": 16,
"unresolvedFailureCount": 6
}
},
"recentProfileCombinationStats": {
@@ -6765,15 +6765,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1482,
"totalRecords": 1566,
"terminalRecords": 1484,
"totalRecords": 1568,
"totals": {
"attributableFailureCount": 391,
"decisionFailureRate": 0.8907,
"decisionSuccessRate": 0.1093,
"decisionTotal": 439,
"failureBreakdown": {
"ambiguous_runtime": 274,
"ambiguous_runtime": 276,
"backend_operator": 25,
"framework_architecture_unsupported": 267,
"memory_capacity": 11,
@@ -6785,21 +6785,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1434,
"failureRate": 0.9676,
"failureCount": 1436,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0324,
"total": 1482,
"unresolvedFailureCount": 1041
"successRate": 0.0323,
"total": 1484,
"unresolvedFailureCount": 1043
},
"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。",
@@ -6807,7 +6807,7 @@
"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。",
@@ -6828,6 +6828,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1566,
"summarizedRecords": 1568,
"version": 1
}