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

state: generation 19010 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-01 01:13:22 +00:00
parent 790f49c308
commit af8103679f
9 changed files with 1360 additions and 1388 deletions
Download Patch File Download Diff File Expand all files Collapse all files

231
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-30T23:01:56.806499+00:00",
"lastSyncTime": "2026-09-30T23:01:56.540688+00:00",
"generatedAt": "2026-10-01T01:11:14.215846+00:00",
"lastSyncTime": "2026-10-01T01:11:13.658711+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3448,25 +3448,25 @@
"decisionSuccessRate": 0.093,
"decisionTotal": 43,
"failureBreakdown": {
"ambiguous_runtime": 77,
"ambiguous_runtime": 79,
"context_length": 8,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 8
},
"failureCount": 125,
"failureRate": 0.969,
"failureCount": 127,
"failureRate": 0.9695,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.031,
"successRate": 0.0305,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 129,
"unresolvedFailureCount": 85
"total": 131,
"unresolvedFailureCount": 87
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 69,
@@ -5465,18 +5465,18 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 117,
"attributableFailureCount": 118,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 117,
"decisionTotal": 118,
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"platform_infrastructure": 22,
"tokenizer_compatibility": 91,
"参数/模板问题": 6
},
"failureCount": 145,
"failureCount": 146,
"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": 145,
"total": 146,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6143,28 +6143,28 @@
"unresolvedFailureCount": 28
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 156,
"decisionFailureRate": 0.9689,
"decisionSuccessRate": 0.0311,
"decisionTotal": 161,
"attributableFailureCount": 157,
"decisionFailureRate": 0.9691,
"decisionSuccessRate": 0.0309,
"decisionTotal": 162,
"failureBreakdown": {
"ambiguous_runtime": 337,
"backend_operator": 9,
"framework_architecture_unsupported": 37,
"framework_architecture_unsupported": 38,
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 22,
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 528,
"failureCount": 529,
"failureRate": 0.9906,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 22,
"successCount": 5,
"successRate": 0.0094,
"total": 533,
"total": 534,
"unresolvedFailureCount": 350
},
"vllm_tokenizer_patch": {
@@ -6173,7 +6173,7 @@
"decisionSuccessRate": 0.068,
"decisionTotal": 147,
"failureBreakdown": {
"ambiguous_runtime": 189,
"ambiguous_runtime": 191,
"backend_operator": 15,
"context_length": 8,
"framework_architecture_unsupported": 81,
@@ -6185,18 +6185,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 358,
"failureRate": 0.9728,
"failureCount": 360,
"failureRate": 0.973,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0272,
"total": 368,
"unresolvedFailureCount": 218
"successRate": 0.027,
"total": 370,
"unresolvedFailureCount": 220
}
},
"generatedAt": "2026-09-30T23:01:56.793295+00:00",
"generatedAt": "2026-10-01T01:11:14.203018+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 109,
@@ -6204,7 +6204,7 @@
"decisionSuccessRate": 0.1679,
"decisionTotal": 131,
"failureBreakdown": {
"ambiguous_runtime": 145,
"ambiguous_runtime": 147,
"context_length": 8,
"framework_architecture_unsupported": 95,
"memory_capacity": 2,
@@ -6215,15 +6215,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 324,
"failureRate": 0.9364,
"failureCount": 326,
"failureRate": 0.9368,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0636,
"total": 346,
"unresolvedFailureCount": 214
"successRate": 0.0632,
"total": 348,
"unresolvedFailureCount": 216
},
"Ascend_910-b4": {
"attributableFailureCount": 325,
@@ -6532,16 +6532,16 @@
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 753,
"decisionFailureRate": 0.888,
"decisionSuccessRate": 0.112,
"decisionTotal": 848,
"attributableFailureCount": 754,
"decisionFailureRate": 0.8881,
"decisionSuccessRate": 0.1119,
"decisionTotal": 849,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 37,
"context_length": 39,
"framework_architecture_unsupported": 162,
"framework_architecture_unsupported": 163,
"memory_capacity": 113,
"platform_infrastructure": 231,
"repository_structure": 83,
@@ -6550,14 +6550,14 @@
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1406,
"failureRate": 0.9367,
"failureCount": 1407,
"failureRate": 0.9368,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 231,
"successCount": 95,
"successRate": 0.0633,
"total": 1501,
"successRate": 0.0632,
"total": 1502,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -6710,9 +6710,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 11
"ambiguous_runtime": 12
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "gemma2",
@@ -6724,8 +6724,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
"total": 12,
"unresolvedFailureCount": 12
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -6894,10 +6894,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 15,
"context_length": 6
},
"failureCount": 20,
"failureCount": 21,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
@@ -6909,8 +6909,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 14
"total": 21,
"unresolvedFailureCount": 15
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -21434,14 +21434,14 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
@@ -21453,7 +21453,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
@@ -23690,11 +23690,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 11,
"context_length": 2,
"framework_architecture_unsupported": 1
},
"failureCount": 12,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -23706,8 +23706,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 9
"total": 14,
"unresolvedFailureCount": 11
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -24026,9 +24026,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -24040,8 +24040,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation": {
"attributableFailureCount": 5,
@@ -24469,11 +24469,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 4,
"model_load": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -24485,8 +24485,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 2
"total": 6,
"unresolvedFailureCount": 1
}
},
"recentProfileCombinationStats": {
@@ -24497,12 +24497,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T15:29:22.559055+00:00",
"lastTerminalAt": "2026-10-01T01:11:13.658662+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -24512,8 +24512,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 2,
@@ -24522,10 +24522,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 4,
"context_length": 2
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-30T15:29:22.559035+00:00",
@@ -24538,8 +24538,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 3
"total": 6,
"unresolvedFailureCount": 4
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 0,
@@ -25691,31 +25691,6 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-23T04:49:01.469123+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -27767,9 +27742,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
@@ -27782,8 +27757,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -28224,9 +28199,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 9
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
@@ -28239,8 +28214,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 9,
"unresolvedFailureCount": 9
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": {
"attributableFailureCount": 0,
@@ -50497,14 +50472,14 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -50517,7 +50492,7 @@
"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|none|35": {
@@ -53885,20 +53860,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17172,
"totalRecords": 17393,
"terminalRecords": 17175,
"totalRecords": 17396,
"totals": {
"attributableFailureCount": 6154,
"decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368,
"decisionTotal": 7129,
"attributableFailureCount": 6155,
"decisionFailureRate": 0.8633,
"decisionSuccessRate": 0.1367,
"decisionTotal": 7130,
"failureBreakdown": {
"ambiguous_runtime": 4477,
"ambiguous_runtime": 4479,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 326,
"framework_architecture_unsupported": 2201,
"framework_architecture_unsupported": 2202,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 943,
@@ -53909,30 +53884,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16197,
"failureCount": 16200,
"failureRate": 0.9432,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 943,
"successCount": 975,
"successRate": 0.0568,
"total": 17172,
"unresolvedFailureCount": 9100
"total": 17175,
"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 Vastai_va16 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 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。",
@@ -53977,6 +53952,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17393,
"summarizedRecords": 17396,
"version": 1
}