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

state: generation 19475 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-02 03:02:21 +00:00
parent 409aa662fa
commit d4d40c4a40
9 changed files with 1218 additions and 1172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

111
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-02T02:51:37.717357+00:00",
"lastSyncTime": "2026-10-02T02:51:37.460235+00:00",
"generatedAt": "2026-10-02T03:00:06.274687+00:00",
"lastSyncTime": "2026-10-02T03:00:05.603502+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5492,16 +5492,16 @@
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 618,
"attributableFailureCount": 619,
"decisionFailureRate": 0.9952,
"decisionSuccessRate": 0.0048,
"decisionTotal": 621,
"decisionTotal": 622,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
"backend_operator": 28,
"context_length": 34,
"framework_architecture_unsupported": 144,
"framework_architecture_unsupported": 145,
"memory_capacity": 113,
"platform_infrastructure": 212,
"repository_structure": 75,
@@ -5509,7 +5509,7 @@
"tokenizer_compatibility": 180,
"参数/模板问题": 9
},
"failureCount": 948,
"failureCount": 949,
"failureRate": 0.9968,
"framework": "vllm",
"pendingCount": 0,
@@ -5519,7 +5519,7 @@
"successRate": 0.0032,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 951,
"total": 952,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -6021,17 +6021,17 @@
"unresolvedFailureCount": 6473
},
"vllm": {
"attributableFailureCount": 3639,
"attributableFailureCount": 3640,
"decisionFailureRate": 0.9725,
"decisionSuccessRate": 0.0275,
"decisionTotal": 3742,
"decisionTotal": 3743,
"failureBreakdown": {
"ambiguous_runtime": 1594,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 93,
"context_length": 161,
"framework_architecture_unsupported": 1368,
"framework_architecture_unsupported": 1369,
"memory_capacity": 725,
"model_load": 221,
"platform_infrastructure": 876,
@@ -6040,14 +6040,14 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6159,
"failureCount": 6160,
"failureRate": 0.9836,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 876,
"successCount": 103,
"successRate": 0.0164,
"total": 6262,
"total": 6263,
"unresolvedFailureCount": 1644
},
"vllm-customized": {
@@ -6198,7 +6198,7 @@
"unresolvedFailureCount": 227
}
},
"generatedAt": "2026-10-02T02:51:37.703119+00:00",
"generatedAt": "2026-10-02T03:00:06.260498+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 114,
@@ -6534,16 +6534,16 @@
"unresolvedFailureCount": 301
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 757,
"decisionFailureRate": 0.8875,
"decisionSuccessRate": 0.1125,
"decisionTotal": 853,
"attributableFailureCount": 758,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 854,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 37,
"context_length": 39,
"framework_architecture_unsupported": 165,
"framework_architecture_unsupported": 166,
"memory_capacity": 113,
"platform_infrastructure": 235,
"repository_structure": 83,
@@ -6552,14 +6552,14 @@
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1414,
"failureRate": 0.9364,
"failureCount": 1415,
"failureRate": 0.9365,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 235,
"successCount": 96,
"successRate": 0.0636,
"total": 1510,
"successRate": 0.0635,
"total": 1511,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -22103,6 +22103,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -51922,6 +51945,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|spark2_5|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -54808,20 +54855,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17225,
"totalRecords": 17446,
"terminalRecords": 17226,
"totalRecords": 17447,
"totals": {
"attributableFailureCount": 6174,
"attributableFailureCount": 6175,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7150,
"decisionTotal": 7151,
"failureBreakdown": {
"ambiguous_runtime": 4505,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 327,
"framework_architecture_unsupported": 2216,
"framework_architecture_unsupported": 2217,
"memory_capacity": 1206,
"model_load": 553,
"platform_infrastructure": 947,
@@ -54832,30 +54879,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16249,
"failureCount": 16250,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 947,
"successCount": 976,
"successRate": 0.0567,
"total": 17225,
"total": 17226,
"unresolvedFailureCount": 9128
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 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-x8 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 Kunlunxin_p-800 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 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。",
"GPU MetaX_c-500 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -54900,6 +54947,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17446,
"summarizedRecords": 17447,
"version": 1
}