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

state: generation 29833 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-22 18:33:49 +00:00
parent 6a8b37dd2e
commit 5e19b412d7
7 changed files with 157 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

187
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-22T18:30:15.227273+00:00",
"lastSyncTime": "2026-10-22T18:30:14.958353+00:00",
"generatedAt": "2026-10-22T18:33:48.534021+00:00",
"lastSyncTime": "2026-10-22T18:33:48.248316+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2656,30 +2656,30 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 140,
"decisionFailureRate": 0.9859,
"decisionSuccessRate": 0.0141,
"decisionTotal": 142,
"attributableFailureCount": 142,
"decisionFailureRate": 0.9861,
"decisionSuccessRate": 0.0139,
"decisionTotal": 144,
"failureBreakdown": {
"ambiguous_runtime": 3,
"backend_operator": 11,
"framework_architecture_unsupported": 31,
"framework_architecture_unsupported": 32,
"memory_capacity": 1,
"platform_infrastructure": 35,
"tokenizer_compatibility": 97,
"tokenizer_compatibility": 98,
"参数/模板问题": 10
},
"failureCount": 188,
"failureRate": 0.9895,
"failureCount": 190,
"failureRate": 0.9896,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 35,
"successCount": 2,
"successRate": 0.0105,
"successRate": 0.0104,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 190,
"total": 192,
"unresolvedFailureCount": 13
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -3337,28 +3337,28 @@
"unresolvedFailureCount": 59
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 189,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 196,
"attributableFailureCount": 191,
"decisionFailureRate": 0.9646,
"decisionSuccessRate": 0.0354,
"decisionTotal": 198,
"failureBreakdown": {
"ambiguous_runtime": 436,
"backend_operator": 11,
"framework_architecture_unsupported": 57,
"framework_architecture_unsupported": 58,
"memory_capacity": 11,
"model_load": 13,
"platform_infrastructure": 35,
"tokenizer_compatibility": 97,
"tokenizer_compatibility": 98,
"参数/模板问题": 33
},
"failureCount": 693,
"failureCount": 695,
"failureRate": 0.99,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 35,
"successCount": 7,
"successRate": 0.01,
"total": 700,
"total": 702,
"unresolvedFailureCount": 469
},
"vllm_tokenizer_patch": {
@@ -3390,7 +3390,7 @@
"unresolvedFailureCount": 341
}
},
"generatedAt": "2026-10-22T18:30:15.212000+00:00",
"generatedAt": "2026-10-22T18:33:48.520963+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 133,
@@ -3727,32 +3727,32 @@
"unresolvedFailureCount": 334
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 794,
"decisionFailureRate": 0.8822,
"decisionSuccessRate": 0.1178,
"decisionTotal": 900,
"attributableFailureCount": 796,
"decisionFailureRate": 0.8825,
"decisionSuccessRate": 0.1175,
"decisionTotal": 902,
"failureBreakdown": {
"ambiguous_runtime": 165,
"architecture_compatibility": 44,
"backend_operator": 44,
"context_length": 39,
"framework_architecture_unsupported": 187,
"framework_architecture_unsupported": 188,
"memory_capacity": 114,
"platform_infrastructure": 259,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 282,
"tokenizer_compatibility": 283,
"参数/模板问题": 233,
"验证失败": 32
},
"failureCount": 1483,
"failureRate": 0.9333,
"failureCount": 1485,
"failureRate": 0.9334,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 259,
"successCount": 106,
"successRate": 0.0667,
"total": 1589,
"successRate": 0.0666,
"total": 1591,
"unresolvedFailureCount": 430
},
"Vastai_va16": {
@@ -21827,6 +21827,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "gemma4_unified",
"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_fix_tokenizer|text-generation|gemma4_unified|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -21991,13 +22014,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 0.3333,
"decisionSuccessRate": 0.6667,
"decisionTotal": 3,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 0.3333,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
"pendingCount": 0,
@@ -22005,10 +22030,10 @@
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 1.0,
"successRate": 0.6667,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|mini_k3|none": {
@@ -55340,6 +55365,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "gemma4_unified",
"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_fix_tokenizer|text-generation|gemma4_unified|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -55677,6 +55726,30 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -60722,42 +60795,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17975,
"totalRecords": 18516,
"terminalRecords": 17977,
"totalRecords": 18518,
"totals": {
"attributableFailureCount": 6358,
"decisionFailureRate": 0.8657,
"decisionSuccessRate": 0.1343,
"decisionTotal": 7344,
"attributableFailureCount": 6360,
"decisionFailureRate": 0.8658,
"decisionSuccessRate": 0.1342,
"decisionTotal": 7346,
"failureBreakdown": {
"ambiguous_runtime": 4670,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 136,
"context_length": 328,
"framework_architecture_unsupported": 2356,
"framework_architecture_unsupported": 2357,
"memory_capacity": 1207,
"model_load": 577,
"platform_infrastructure": 971,
"repository_structure": 742,
"runtime_memory": 101,
"tokenizer_compatibility": 696,
"tokenizer_compatibility": 697,
"参数/模板问题": 3595,
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16989,
"failureRate": 0.9451,
"failureCount": 16991,
"failureRate": 0.9452,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 971,
"successCount": 986,
"successRate": 0.0549,
"total": 17975,
"successRate": 0.0548,
"total": 17977,
"unresolvedFailureCount": 9660
},
"warnings": [
"GPU Vastai_va16 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 Kunlunxin_p-800 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。",
@@ -60770,6 +60842,7 @@
"GPU Iluvatar_mrv-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 Vastai_va16 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。",
"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。",
"组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -60786,7 +60859,9 @@
"组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_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 Kunlunxin_p-800|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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|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 Cambricon_mlu-370-x8|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 Iluvatar_bi-150|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 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。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -60811,12 +60886,10 @@
"组合 Cambricon_mlu-370-x8|vllm-mlu|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-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|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_bi-150|vllm_fix_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 Cambricon_mlu-370-x8|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-customized|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_bi-150|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18516,
"summarizedRecords": 18518,
"version": 1
}