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

state: generation 13338 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-23 03:22:52 +00:00
parent 5639328f60
commit ae3a17ca6f
9 changed files with 1873 additions and 1853 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-23T02:43:28.816899+00:00",
"lastSyncTime": "2026-09-23T02:43:25.562726+00:00",
"generatedAt": "2026-09-23T03:22:39.773217+00:00",
"lastSyncTime": "2026-09-23T03:22:39.362176+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4700,10 +4700,10 @@
"unresolvedFailureCount": 132
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 40,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 45,
"attributableFailureCount": 41,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 8,
@@ -4712,20 +4712,20 @@
"model_load": 12,
"platform_infrastructure": 1,
"repository_structure": 2,
"runtime_memory": 2,
"runtime_memory": 3,
"参数/模板问题": 14
},
"failureCount": 60,
"failureRate": 0.9231,
"failureCount": 61,
"failureRate": 0.9242,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 5,
"successRate": 0.0769,
"successRate": 0.0758,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 65,
"total": 66,
"unresolvedFailureCount": 19
},
"Kunlunxin_p-800|vllm|text-generation": {
@@ -5860,10 +5860,10 @@
"unresolvedFailureCount": 313
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 107,
"decisionFailureRate": 0.9304,
"decisionSuccessRate": 0.0696,
"decisionTotal": 115,
"attributableFailureCount": 108,
"decisionFailureRate": 0.931,
"decisionSuccessRate": 0.069,
"decisionTotal": 116,
"failureBreakdown": {
"ambiguous_runtime": 147,
"backend_operator": 8,
@@ -5873,22 +5873,22 @@
"model_load": 15,
"platform_infrastructure": 2,
"repository_structure": 3,
"runtime_memory": 2,
"runtime_memory": 3,
"tokenizer_compatibility": 2,
"参数/模板问题": 28
},
"failureCount": 284,
"failureRate": 0.9726,
"failureCount": 285,
"failureRate": 0.9727,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 8,
"successRate": 0.0274,
"total": 292,
"successRate": 0.0273,
"total": 293,
"unresolvedFailureCount": 175
}
},
"generatedAt": "2026-09-23T02:43:28.804947+00:00",
"generatedAt": "2026-09-23T03:22:39.761537+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6114,10 +6114,10 @@
"unresolvedFailureCount": 717
},
"Kunlunxin_p-800": {
"attributableFailureCount": 54,
"decisionFailureRate": 0.9153,
"decisionSuccessRate": 0.0847,
"decisionTotal": 59,
"attributableFailureCount": 55,
"decisionFailureRate": 0.9167,
"decisionSuccessRate": 0.0833,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 210,
"backend_operator": 11,
@@ -6126,19 +6126,19 @@
"model_load": 13,
"platform_infrastructure": 1,
"repository_structure": 2,
"runtime_memory": 2,
"runtime_memory": 3,
"参数/模板问题": 32,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 321,
"failureCount": 322,
"failureRate": 0.9847,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 5,
"successRate": 0.0153,
"total": 326,
"total": 327,
"unresolvedFailureCount": 266
},
"Kunlunxin_r-200-8f": {
@@ -17055,14 +17055,15 @@
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"model_load": 1
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -17074,7 +17075,7 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
@@ -40555,6 +40556,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none|36": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 36,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -45897,13 +45922,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16799,
"totalRecords": 17017,
"terminalRecords": 16800,
"totalRecords": 17018,
"totals": {
"attributableFailureCount": 6013,
"attributableFailureCount": 6014,
"decisionFailureRate": 0.8622,
"decisionSuccessRate": 0.1378,
"decisionTotal": 6974,
"decisionTotal": 6975,
"failureBreakdown": {
"ambiguous_runtime": 4286,
"architecture_compatibility": 212,
@@ -45915,25 +45940,26 @@
"model_load": 526,
"platform_infrastructure": 931,
"repository_structure": 740,
"runtime_memory": 91,
"runtime_memory": 92,
"tokenizer_compatibility": 669,
"参数/模板问题": 3213,
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 15838,
"failureCount": 15839,
"failureRate": 0.9428,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 931,
"successCount": 961,
"successRate": 0.0572,
"total": 16799,
"total": 16800,
"unresolvedFailureCount": 8894
},
"warnings": [
"GPU Iluvatar_mrv-100 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 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-x8 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。",
@@ -45944,7 +45970,6 @@
"GPU Vastai_va16 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 Biren_166m 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。",
"组合 Iluvatar_bi-150|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。",
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -45968,6 +45993,7 @@
"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 MetaX_c-500|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。",
"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 Ascend_910-b4|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。",
"组合 Sunrise_pt-200-x1|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 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。",
@@ -45981,11 +46007,10 @@
"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 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 MetaX_c-500|vllm|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 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-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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17017,
"summarizedRecords": 17018,
"version": 1
}