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

state: generation 8289 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-16 16:44:47 +00:00
parent dedf1d69bf
commit 7e9719873f
9 changed files with 1945 additions and 1947 deletions
Download Patch File Download Diff File Expand all files Collapse all files

108
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-16T16:08:21.811082+00:00",
"lastSyncTime": "2026-09-16T16:08:21.748785+00:00",
"generatedAt": "2026-09-16T16:42:47.816275+00:00",
"lastSyncTime": "2026-09-16T16:42:46.012489+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1928,25 +1928,25 @@
"unresolvedFailureCount": 59
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 14,
"attributableFailureCount": 14,
"decisionFailureRate": 0.9333,
"decisionSuccessRate": 0.0667,
"decisionTotal": 15,
"failureBreakdown": {
"framework_architecture_unsupported": 8,
"framework_architecture_unsupported": 9,
"model_load": 5
},
"failureCount": 13,
"failureRate": 0.9286,
"failureCount": 14,
"failureRate": 0.9333,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0714,
"successRate": 0.0667,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2786,14 +2786,14 @@
"unresolvedFailureCount": 903
},
"vllm": {
"attributableFailureCount": 366,
"decisionFailureRate": 0.9606,
"decisionSuccessRate": 0.0394,
"decisionTotal": 381,
"attributableFailureCount": 367,
"decisionFailureRate": 0.9607,
"decisionSuccessRate": 0.0393,
"decisionTotal": 382,
"failureBreakdown": {
"ambiguous_runtime": 222,
"backend_operator": 35,
"framework_architecture_unsupported": 270,
"framework_architecture_unsupported": 271,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2802,14 +2802,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 31
},
"failureCount": 621,
"failureRate": 0.9764,
"failureCount": 622,
"failureRate": 0.9765,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0236,
"total": 636,
"successRate": 0.0235,
"total": 637,
"unresolvedFailureCount": 253
},
"vllm-mlu": {
@@ -2920,7 +2920,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T16:08:21.805748+00:00",
"generatedAt": "2026-09-16T16:42:47.811297+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2971,28 +2971,28 @@
"unresolvedFailureCount": 231
},
"Biren_166m": {
"attributableFailureCount": 49,
"decisionFailureRate": 0.9423,
"decisionSuccessRate": 0.0577,
"decisionTotal": 52,
"attributableFailureCount": 50,
"decisionFailureRate": 0.9434,
"decisionSuccessRate": 0.0566,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 31,
"backend_operator": 4,
"framework_architecture_unsupported": 35,
"framework_architecture_unsupported": 36,
"memory_capacity": 1,
"model_load": 8,
"tokenizer_compatibility": 1,
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 108,
"failureRate": 0.973,
"failureCount": 109,
"failureRate": 0.9732,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.027,
"total": 111,
"successRate": 0.0268,
"total": 112,
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
@@ -3526,14 +3526,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors": {
"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",
"modelType": "qwen3_5",
@@ -3545,7 +3545,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|escha": {
@@ -7143,14 +7143,14 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"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",
"loadSizeLog2Bucket": 33,
@@ -7163,7 +7163,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|34": {
@@ -10969,17 +10969,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2030,
"totalRecords": 2124,
"terminalRecords": 2031,
"totalRecords": 2125,
"totals": {
"attributableFailureCount": 652,
"decisionFailureRate": 0.8919,
"decisionSuccessRate": 0.1081,
"decisionTotal": 731,
"attributableFailureCount": 653,
"decisionFailureRate": 0.8921,
"decisionSuccessRate": 0.1079,
"decisionTotal": 732,
"failureBreakdown": {
"ambiguous_runtime": 492,
"backend_operator": 45,
"framework_architecture_unsupported": 427,
"framework_architecture_unsupported": 428,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -10989,29 +10989,29 @@
"参数/模板问题": 124,
"验证失败": 673
},
"failureCount": 1951,
"failureCount": 1952,
"failureRate": 0.9611,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 79,
"successRate": 0.0389,
"total": 2030,
"total": 2031,
"unresolvedFailureCount": 1289
},
"warnings": [
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 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 Ascend_910-b4 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 Iluvatar_mrv-100 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-150 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 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 Ascend_910-b3 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 Vastai_va16 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 Biren_166m|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 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。",
@@ -11036,6 +11036,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2124,
"summarizedRecords": 2125,
"version": 1
}