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

state: generation 6173 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 11:25:08 +00:00
parent 06e339d503
commit a492ac892f
9 changed files with 2211 additions and 2211 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-12T10:56:57.261167+00:00",
"lastSyncTime": "2026-09-12T10:56:57.011705+00:00",
"generatedAt": "2026-09-12T11:23:23.405574+00:00",
"lastSyncTime": "2026-09-12T11:23:23.155704+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2330,14 +2330,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 31,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 59,
"failureCount": 60,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2347,8 +2347,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 59,
"unresolvedFailureCount": 17
"total": 60,
"unresolvedFailureCount": 18
}
},
"frameworkSummaries": {
@@ -2421,7 +2421,7 @@
"decisionSuccessRate": 0.0111,
"decisionTotal": 271,
"failureBreakdown": {
"ambiguous_runtime": 199,
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 184,
"memory_capacity": 6,
@@ -2432,15 +2432,15 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 492,
"failureRate": 0.9939,
"failureCount": 493,
"failureRate": 0.994,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0061,
"total": 495,
"unresolvedFailureCount": 223
"successRate": 0.006,
"total": 496,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2544,7 +2544,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T10:56:57.257120+00:00",
"generatedAt": "2026-09-12T11:23:23.400496+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2856,7 +2856,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 34,
"memory_capacity": 1,
"model_load": 4,
@@ -2865,15 +2865,15 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 100,
"failureCount": 101,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 100,
"unresolvedFailureCount": 55
"total": 101,
"unresolvedFailureCount": 56
}
},
"observedGpuMemoryGiB": {
@@ -4561,19 +4561,19 @@
"unresolvedFailureCount": 19
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4585,7 +4585,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 5,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -4811,7 +4811,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T09:16:13.411459+00:00",
"lastTerminalAt": "2026-09-12T11:23:23.155704+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7208,15 +7208,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1715,
"totalRecords": 1802,
"terminalRecords": 1716,
"totalRecords": 1803,
"totals": {
"attributableFailureCount": 478,
"decisionFailureRate": 0.8935,
"decisionSuccessRate": 0.1065,
"decisionTotal": 535,
"failureBreakdown": {
"ambiguous_runtime": 402,
"ambiguous_runtime": 403,
"backend_operator": 42,
"framework_architecture_unsupported": 293,
"memory_capacity": 11,
@@ -7228,20 +7228,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1658,
"failureCount": 1659,
"failureRate": 0.9668,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0332,
"total": 1715,
"unresolvedFailureCount": 1176
"total": 1716,
"unresolvedFailureCount": 1177
},
"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。",
@@ -7250,7 +7251,6 @@
"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。",
@@ -7272,6 +7272,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1802,
"summarizedRecords": 1803,
"version": 1
}