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

state: generation 17771 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 06:28:51 +00:00
parent 32df9e880f
commit f9f87b4d6d
8 changed files with 1353 additions and 1328 deletions
Download Patch File Download Diff File Expand all files Collapse all files

149
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T06:15:43.739437+00:00",
"lastSyncTime": "2026-09-28T06:15:43.444013+00:00",
"generatedAt": "2026-09-28T06:26:41.614385+00:00",
"lastSyncTime": "2026-09-28T06:26:41.357416+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5422,18 +5422,18 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 114,
"attributableFailureCount": 115,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 114,
"decisionTotal": 115,
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"platform_infrastructure": 20,
"tokenizer_compatibility": 91,
"参数/模板问题": 6
},
"failureCount": 140,
"failureCount": 141,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -5443,20 +5443,20 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 140,
"total": 141,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 615,
"attributableFailureCount": 616,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 615,
"decisionTotal": 616,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
"backend_operator": 28,
"context_length": 34,
"framework_architecture_unsupported": 142,
"framework_architecture_unsupported": 143,
"memory_capacity": 113,
"platform_infrastructure": 207,
"repository_structure": 75,
@@ -5464,7 +5464,7 @@
"tokenizer_compatibility": 179,
"参数/模板问题": 9
},
"failureCount": 940,
"failureCount": 941,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -5474,7 +5474,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 940,
"total": 941,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5976,17 +5976,17 @@
"unresolvedFailureCount": 6473
},
"vllm": {
"attributableFailureCount": 3625,
"attributableFailureCount": 3626,
"decisionFailureRate": 0.9739,
"decisionSuccessRate": 0.0261,
"decisionTotal": 3722,
"decisionTotal": 3723,
"failureBreakdown": {
"ambiguous_runtime": 1585,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 93,
"context_length": 161,
"framework_architecture_unsupported": 1359,
"framework_architecture_unsupported": 1360,
"memory_capacity": 725,
"model_load": 220,
"platform_infrastructure": 871,
@@ -5995,14 +5995,14 @@
"tokenizer_compatibility": 416,
"参数/模板问题": 50
},
"failureCount": 6131,
"failureCount": 6132,
"failureRate": 0.9844,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 871,
"successCount": 97,
"successRate": 0.0156,
"total": 6228,
"total": 6229,
"unresolvedFailureCount": 1635
},
"vllm-customized": {
@@ -6100,28 +6100,28 @@
"unresolvedFailureCount": 25
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 151,
"decisionFailureRate": 0.9679,
"decisionSuccessRate": 0.0321,
"decisionTotal": 156,
"attributableFailureCount": 152,
"decisionFailureRate": 0.9682,
"decisionSuccessRate": 0.0318,
"decisionTotal": 157,
"failureBreakdown": {
"ambiguous_runtime": 320,
"backend_operator": 9,
"framework_architecture_unsupported": 32,
"framework_architecture_unsupported": 33,
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 20,
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 504,
"failureCount": 505,
"failureRate": 0.9902,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 20,
"successCount": 5,
"successRate": 0.0098,
"total": 509,
"total": 510,
"unresolvedFailureCount": 333
},
"vllm_tokenizer_patch": {
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T06:15:43.725831+00:00",
"generatedAt": "2026-09-28T06:26:41.601640+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6488,16 +6488,16 @@
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 748,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 841,
"attributableFailureCount": 750,
"decisionFailureRate": 0.8897,
"decisionSuccessRate": 0.1103,
"decisionTotal": 843,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 37,
"context_length": 39,
"framework_architecture_unsupported": 158,
"framework_architecture_unsupported": 160,
"memory_capacity": 113,
"platform_infrastructure": 227,
"repository_structure": 83,
@@ -6506,14 +6506,14 @@
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1397,
"failureRate": 0.9376,
"failureCount": 1399,
"failureRate": 0.9377,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 227,
"successCount": 93,
"successRate": 0.0624,
"total": 1490,
"successRate": 0.0623,
"total": 1492,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -20771,14 +20771,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
@@ -20790,7 +20791,7 @@
"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_mtp|none": {
@@ -21072,14 +21073,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|zaya|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "zaya",
@@ -21091,7 +21093,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|cohere2|none": {
@@ -48536,6 +48538,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|35": {
"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": 35,
"modelType": "qwen3_5_moe",
"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|qwen3_5_mtp|none|27": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -48947,14 +48973,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|zaya|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -48967,7 +48994,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|cohere2|none|32": {
@@ -51639,20 +51666,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17072,
"totalRecords": 17293,
"terminalRecords": 17074,
"totalRecords": 17295,
"totals": {
"attributableFailureCount": 6119,
"attributableFailureCount": 6121,
"decisionFailureRate": 0.8637,
"decisionSuccessRate": 0.1363,
"decisionTotal": 7085,
"decisionTotal": 7087,
"failureBreakdown": {
"ambiguous_runtime": 4426,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2175,
"framework_architecture_unsupported": 2177,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 938,
@@ -51663,14 +51690,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16106,
"failureCount": 16108,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17072,
"total": 17074,
"unresolvedFailureCount": 9049
},
"warnings": [
@@ -51679,15 +51706,15 @@
"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 MetaX_c-500 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 Vastai_va16 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 Ascend_910-b3 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 Biren_166m 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 Iluvatar_bi-100 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 Mthreads_s4000 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。",
"组合 Ascend_910-b3|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 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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51711,6 +51738,7 @@
"组合 Cambricon_mlu-370-x4|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|transformers|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-patch-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 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 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 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。",
"组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51724,11 +51752,10 @@
"组合 Cambricon_mlu-370-x4|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|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 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。",
"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 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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17293,
"summarizedRecords": 17295,
"version": 1
}