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

state: generation 5176 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 13:16:02 +00:00
parent 0df966fc90
commit 32c0017465
10 changed files with 2153 additions and 2154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

92
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T13:06:08.640092+00:00",
"lastSyncTime": "2026-09-10T13:06:08.293484+00:00",
"generatedAt": "2026-09-10T13:14:20.211520+00:00",
"lastSyncTime": "2026-09-10T13:14:20.004672+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1596,11 +1596,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 7,
"参数/模板问题": 3
},
"failureCount": 27,
"failureCount": 28,
"failureRate": 1.0,
"framework": "vllm-mlu",
"pendingCount": 0,
@@ -1610,8 +1610,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 27,
"unresolvedFailureCount": 20
"total": 28,
"unresolvedFailureCount": 21
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -2348,19 +2348,19 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 7,
"参数/模板问题": 3
},
"failureCount": 27,
"failureCount": 28,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 27,
"unresolvedFailureCount": 20
"total": 28,
"unresolvedFailureCount": 21
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 3,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T13:06:08.636229+00:00",
"generatedAt": "2026-09-10T13:14:20.207683+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2545,22 +2545,22 @@
"decisionSuccessRate": 0.1053,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 36,
"ambiguous_runtime": 37,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 93,
"failureRate": 0.9789,
"failureCount": 94,
"failureRate": 0.9792,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0211,
"total": 95,
"unresolvedFailureCount": 76
"successRate": 0.0208,
"total": 96,
"unresolvedFailureCount": 77
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -3069,9 +3069,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "starcoder2",
@@ -3083,8 +3083,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
@@ -4150,11 +4150,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 4,
"参数/模板问题": 1
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4166,8 +4166,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 14
"total": 19,
"unresolvedFailureCount": 15
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -4407,13 +4407,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 7,
"backend_operator": 3,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4425,8 +4425,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 8
"total": 13,
"unresolvedFailureCount": 7
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4817,9 +4817,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T16:13:44.313839+00:00",
@@ -4832,8 +4832,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
@@ -5576,9 +5576,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 31,
@@ -5591,8 +5591,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
@@ -7053,15 +7053,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1588,
"totalRecords": 1675,
"terminalRecords": 1589,
"totalRecords": 1676,
"totals": {
"attributableFailureCount": 415,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 466,
"failureBreakdown": {
"ambiguous_runtime": 348,
"ambiguous_runtime": 349,
"backend_operator": 35,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7073,21 +7073,21 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1537,
"failureCount": 1538,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0321,
"total": 1588,
"unresolvedFailureCount": 1119
"total": 1589,
"unresolvedFailureCount": 1120
},
"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。",
@@ -7095,7 +7095,7 @@
"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。",
@@ -7116,6 +7116,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1675,
"summarizedRecords": 1676,
"version": 1
}