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

state: generation 21906 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 15:59:18 +00:00
parent 0267dfd07c
commit 92a5b6df81
10 changed files with 2018 additions and 2019 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T15:15:58.431781+00:00",
"lastSyncTime": "2026-10-07T15:15:58.161969+00:00",
"generatedAt": "2026-10-07T15:52:49.143323+00:00",
"lastSyncTime": "2026-10-07T15:52:48.873111+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4083,10 +4083,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 49,
"ambiguous_runtime": 50,
"memory_capacity": 9
},
"failureCount": 58,
"failureCount": 59,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4096,8 +4096,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 58,
"unresolvedFailureCount": 49
"total": 59,
"unresolvedFailureCount": 50
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 10,
@@ -5633,7 +5633,7 @@
"decisionSuccessRate": 0.0278,
"decisionTotal": 180,
"failureBreakdown": {
"ambiguous_runtime": 370,
"ambiguous_runtime": 371,
"backend_operator": 9,
"framework_architecture_unsupported": 48,
"memory_capacity": 10,
@@ -5642,15 +5642,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 583,
"failureCount": 584,
"failureRate": 0.9915,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0085,
"total": 588,
"unresolvedFailureCount": 383
"total": 589,
"unresolvedFailureCount": 384
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 155,
@@ -5681,7 +5681,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-07T15:15:58.415601+00:00",
"generatedAt": "2026-10-07T15:52:49.127412+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5851,7 +5851,7 @@
"decisionSuccessRate": 0.1639,
"decisionTotal": 915,
"failureBreakdown": {
"ambiguous_runtime": 662,
"ambiguous_runtime": 663,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
@@ -5866,15 +5866,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1954,
"failureCount": 1955,
"failureRate": 0.9287,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0713,
"total": 2104,
"unresolvedFailureCount": 1168
"total": 2105,
"unresolvedFailureCount": 1169
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 984,
@@ -16465,9 +16465,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "mini_k3",
@@ -16479,8 +16479,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 0,
@@ -25496,11 +25496,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 1,
"参数/模板问题": 1
},
"failureCount": 20,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
@@ -25512,8 +25512,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 19
"total": 19,
"unresolvedFailureCount": 18
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
@@ -25600,14 +25600,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"memory_capacity": 2
},
"failureCount": 18,
"failureCount": 19,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-07T13:29:11.757302+00:00",
"lastTerminalAt": "2026-10-07T15:52:48.873111+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25615,8 +25615,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 16
"total": 19,
"unresolvedFailureCount": 17
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
@@ -26875,9 +26875,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-25T01:41:30.953868+00:00",
@@ -26890,8 +26890,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -27575,12 +27575,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T13:29:11.757302+00:00",
"lastTerminalAt": "2026-10-07T15:52:48.873111+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -27590,8 +27590,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -45183,9 +45183,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
@@ -45198,8 +45198,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": {
"attributableFailureCount": 0,
@@ -58305,15 +58305,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17407,
"totalRecords": 17664,
"terminalRecords": 17408,
"totalRecords": 17665,
"totals": {
"attributableFailureCount": 6249,
"decisionFailureRate": 0.8647,
"decisionSuccessRate": 0.1353,
"decisionTotal": 7227,
"failureBreakdown": {
"ambiguous_runtime": 4567,
"ambiguous_runtime": 4568,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -58329,15 +58329,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16429,
"failureCount": 16430,
"failureRate": 0.9438,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0562,
"total": 17407,
"unresolvedFailureCount": 9228
"total": 17408,
"unresolvedFailureCount": 9229
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -58346,14 +58346,14 @@
"GPU hygon_k100-ai 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。",
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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 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 Mthreads_s4000 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。",
"组合 Vastai_va16|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-b3|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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -58398,6 +58398,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17664,
"summarizedRecords": 17665,
"version": 1
}