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

state: generation 6563 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-13 06:00:07 +00:00
parent a72eb7f868
commit b595cc889f
9 changed files with 2036 additions and 2037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T05:49:53.761779+00:00",
"lastSyncTime": "2026-09-13T05:49:53.509642+00:00",
"generatedAt": "2026-09-13T05:58:35.719154+00:00",
"lastSyncTime": "2026-09-13T05:58:35.516166+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2398,19 +2398,19 @@
"unresolvedFailureCount": 8
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 43,
"attributableFailureCount": 44,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 43,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 61,
"failureCount": 62,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2420,7 +2420,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 61,
"total": 62,
"unresolvedFailureCount": 18
}
},
@@ -2489,14 +2489,14 @@
"unresolvedFailureCount": 875
},
"vllm": {
"attributableFailureCount": 293,
"attributableFailureCount": 294,
"decisionFailureRate": 0.9899,
"decisionSuccessRate": 0.0101,
"decisionTotal": 296,
"decisionTotal": 297,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 206,
"framework_architecture_unsupported": 207,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2505,14 +2505,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 519,
"failureCount": 520,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0057,
"total": 522,
"total": 523,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2617,7 +2617,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T05:49:53.757657+00:00",
"generatedAt": "2026-09-13T05:58:35.713501+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2924,13 +2924,13 @@
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
"attributableFailureCount": 47,
"attributableFailureCount": 48,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 47,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 36,
"framework_architecture_unsupported": 37,
"memory_capacity": 1,
"model_load": 4,
"repository_structure": 4,
@@ -2938,14 +2938,14 @@
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 103,
"failureCount": 104,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 103,
"total": 104,
"unresolvedFailureCount": 56
}
},
@@ -5032,15 +5032,15 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 5,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 6,
"model_load": 1,
"repository_structure": 1,
"runtime_memory": 1
@@ -5049,7 +5049,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T00:10:37.716599+00:00",
"lastTerminalAt": "2026-09-13T05:58:35.516166+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5058,7 +5058,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 12
"unresolvedFailureCount": 11
}
},
"recentProfileCombinationStats": {
@@ -7462,17 +7462,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1766,
"totalRecords": 1853,
"terminalRecords": 1767,
"totalRecords": 1854,
"totals": {
"attributableFailureCount": 512,
"decisionFailureRate": 0.8967,
"decisionSuccessRate": 0.1033,
"decisionTotal": 571,
"attributableFailureCount": 513,
"decisionFailureRate": 0.8969,
"decisionSuccessRate": 0.1031,
"decisionTotal": 572,
"failureBreakdown": {
"ambiguous_runtime": 415,
"backend_operator": 43,
"framework_architecture_unsupported": 321,
"framework_architecture_unsupported": 322,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7482,21 +7482,20 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1707,
"failureCount": 1708,
"failureRate": 0.9666,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0334,
"total": 1766,
"total": 1767,
"unresolvedFailureCount": 1191
},
"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。",
@@ -7505,6 +7504,7 @@
"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。",
@@ -7527,6 +7527,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1853,
"summarizedRecords": 1854,
"version": 1
}