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

state: generation 19019 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-01 01:50:34 +00:00
parent a69bf8d760
commit 2c45ceda4c
8 changed files with 1446 additions and 1402 deletions
Download Patch File Download Diff File Expand all files Collapse all files

215
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-01T01:11:14.215846+00:00",
"lastSyncTime": "2026-10-01T01:11:13.658711+00:00",
"generatedAt": "2026-10-01T01:47:37.257974+00:00",
"lastSyncTime": "2026-10-01T01:47:36.964192+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3627,18 +3627,18 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 27,
"attributableFailureCount": 28,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 27,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 98,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"platform_infrastructure": 1,
"repository_structure": 1,
"参数/模板问题": 6
},
"failureCount": 132,
"failureCount": 133,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -3648,7 +3648,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 132,
"total": 133,
"unresolvedFailureCount": 104
},
"Ascend_910-b4|vllm|text-generation": {
@@ -5465,18 +5465,18 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 118,
"attributableFailureCount": 119,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 118,
"decisionTotal": 119,
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 18,
"platform_infrastructure": 22,
"tokenizer_compatibility": 91,
"tokenizer_compatibility": 92,
"参数/模板问题": 6
},
"failureCount": 146,
"failureCount": 147,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -5486,7 +5486,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 146,
"total": 147,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -5501,23 +5501,23 @@
"context_length": 34,
"framework_architecture_unsupported": 143,
"memory_capacity": 113,
"platform_infrastructure": 209,
"platform_infrastructure": 210,
"repository_structure": 75,
"runtime_memory": 1,
"tokenizer_compatibility": 180,
"参数/模板问题": 9
},
"failureCount": 944,
"failureCount": 945,
"failureRate": 0.9979,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 209,
"platformFailureCount": 210,
"successCount": 2,
"successRate": 0.0021,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 946,
"total": 947,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -6032,20 +6032,20 @@
"framework_architecture_unsupported": 1365,
"memory_capacity": 725,
"model_load": 220,
"platform_infrastructure": 873,
"platform_infrastructure": 874,
"repository_structure": 470,
"runtime_memory": 66,
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6147,
"failureCount": 6148,
"failureRate": 0.9837,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 873,
"platformFailureCount": 874,
"successCount": 102,
"successRate": 0.0163,
"total": 6249,
"total": 6250,
"unresolvedFailureCount": 1639
},
"vllm-customized": {
@@ -6143,10 +6143,10 @@
"unresolvedFailureCount": 28
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 157,
"decisionFailureRate": 0.9691,
"decisionSuccessRate": 0.0309,
"decisionTotal": 162,
"attributableFailureCount": 158,
"decisionFailureRate": 0.9693,
"decisionSuccessRate": 0.0307,
"decisionTotal": 163,
"failureBreakdown": {
"ambiguous_runtime": 337,
"backend_operator": 9,
@@ -6154,29 +6154,29 @@
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 22,
"tokenizer_compatibility": 91,
"tokenizer_compatibility": 92,
"参数/模板问题": 13
},
"failureCount": 529,
"failureRate": 0.9906,
"failureCount": 530,
"failureRate": 0.9907,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0094,
"total": 534,
"successRate": 0.0093,
"total": 535,
"unresolvedFailureCount": 350
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 137,
"decisionFailureRate": 0.932,
"decisionSuccessRate": 0.068,
"decisionTotal": 147,
"attributableFailureCount": 138,
"decisionFailureRate": 0.9324,
"decisionSuccessRate": 0.0676,
"decisionTotal": 148,
"failureBreakdown": {
"ambiguous_runtime": 191,
"backend_operator": 15,
"context_length": 8,
"framework_architecture_unsupported": 81,
"framework_architecture_unsupported": 82,
"memory_capacity": 2,
"model_load": 23,
"platform_infrastructure": 3,
@@ -6185,18 +6185,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 360,
"failureCount": 361,
"failureRate": 0.973,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.027,
"total": 370,
"total": 371,
"unresolvedFailureCount": 220
}
},
"generatedAt": "2026-10-01T01:11:14.203018+00:00",
"generatedAt": "2026-10-01T01:47:37.241876+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 109,
@@ -6226,14 +6226,14 @@
"unresolvedFailureCount": 216
},
"Ascend_910-b4": {
"attributableFailureCount": 325,
"decisionFailureRate": 0.8355,
"decisionSuccessRate": 0.1645,
"decisionTotal": 389,
"attributableFailureCount": 326,
"decisionFailureRate": 0.8359,
"decisionSuccessRate": 0.1641,
"decisionTotal": 390,
"failureBreakdown": {
"ambiguous_runtime": 248,
"context_length": 1,
"framework_architecture_unsupported": 181,
"framework_architecture_unsupported": 182,
"memory_capacity": 19,
"model_load": 85,
"platform_infrastructure": 3,
@@ -6243,14 +6243,14 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 1033,
"failureCount": 1034,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 64,
"successRate": 0.0583,
"total": 1097,
"total": 1098,
"unresolvedFailureCount": 705
},
"Biren_166m": {
@@ -6532,10 +6532,10 @@
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 754,
"decisionFailureRate": 0.8881,
"decisionSuccessRate": 0.1119,
"decisionTotal": 849,
"attributableFailureCount": 755,
"decisionFailureRate": 0.8882,
"decisionSuccessRate": 0.1118,
"decisionTotal": 850,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -6543,21 +6543,21 @@
"context_length": 39,
"framework_architecture_unsupported": 163,
"memory_capacity": 113,
"platform_infrastructure": 231,
"platform_infrastructure": 232,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 274,
"tokenizer_compatibility": 275,
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1407,
"failureCount": 1409,
"failureRate": 0.9368,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 231,
"platformFailureCount": 232,
"successCount": 95,
"successRate": 0.0632,
"total": 1502,
"total": 1504,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -8706,6 +8706,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|torchao": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -21386,15 +21409,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"backend_operator": 2,
"tokenizer_compatibility": 2
"tokenizer_compatibility": 3
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -21406,7 +21429,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
@@ -21717,21 +21740,21 @@
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2
"platform_infrastructure": 3
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"platformFailureCount": 3,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": {
@@ -31114,6 +31137,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|torchao|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "torchao",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -50400,14 +50447,14 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -50420,7 +50467,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
@@ -50936,22 +50983,22 @@
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
"platform_infrastructure": 2
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"platformFailureCount": 2,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|13": {
@@ -53860,54 +53907,54 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17175,
"totalRecords": 17396,
"terminalRecords": 17178,
"totalRecords": 17399,
"totals": {
"attributableFailureCount": 6155,
"attributableFailureCount": 6157,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7130,
"decisionTotal": 7132,
"failureBreakdown": {
"ambiguous_runtime": 4479,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"framework_architecture_unsupported": 2202,
"framework_architecture_unsupported": 2203,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 943,
"platform_infrastructure": 944,
"repository_structure": 742,
"runtime_memory": 101,
"tokenizer_compatibility": 685,
"tokenizer_compatibility": 686,
"参数/模板问题": 3228,
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16200,
"failureCount": 16203,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"platformFailureCount": 944,
"successCount": 975,
"successRate": 0.0568,
"total": 17175,
"total": 17178,
"unresolvedFailureCount": 9102
},
"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。",
@@ -53952,6 +53999,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17396,
"summarizedRecords": 17399,
"version": 1
}