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

state: generation 17706 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 03:33:52 +00:00
parent 815bb5e858
commit 5262e5d091
8 changed files with 1670 additions and 1624 deletions
Download Patch File Download Diff File Expand all files Collapse all files

127
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T03:23:38.538672+00:00",
"lastSyncTime": "2026-09-28T03:23:37.959151+00:00",
"generatedAt": "2026-09-28T03:31:38.420170+00:00",
"lastSyncTime": "2026-09-28T03:31:38.156601+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4529,30 +4529,30 @@
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.6842,
"decisionSuccessRate": 0.3158,
"decisionTotal": 57,
"attributableFailureCount": 40,
"decisionFailureRate": 0.6897,
"decisionSuccessRate": 0.3103,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 23,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 64,
"failureRate": 0.7805,
"failureCount": 65,
"failureRate": 0.7831,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2195,
"successRate": 0.2169,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 82,
"total": 83,
"unresolvedFailureCount": 25
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -6057,27 +6057,27 @@
"unresolvedFailureCount": 52
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.6842,
"decisionSuccessRate": 0.3158,
"decisionTotal": 57,
"attributableFailureCount": 40,
"decisionFailureRate": 0.6897,
"decisionSuccessRate": 0.3103,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 23,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 64,
"failureRate": 0.7805,
"failureCount": 65,
"failureRate": 0.7831,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2195,
"total": 82,
"successRate": 0.2169,
"total": 83,
"unresolvedFailureCount": 25
},
"vllm_fix_tokenizer": {
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T03:23:38.526090+00:00",
"generatedAt": "2026-09-28T03:31:38.406685+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6298,16 +6298,16 @@
"unresolvedFailureCount": 568
},
"Iluvatar_bi-150": {
"attributableFailureCount": 756,
"decisionFailureRate": 0.8354,
"decisionSuccessRate": 0.1646,
"decisionTotal": 905,
"attributableFailureCount": 757,
"decisionFailureRate": 0.8355,
"decisionSuccessRate": 0.1645,
"decisionTotal": 906,
"failureBreakdown": {
"ambiguous_runtime": 650,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
"framework_architecture_unsupported": 250,
"framework_architecture_unsupported": 251,
"memory_capacity": 153,
"model_load": 126,
"platform_infrastructure": 21,
@@ -6318,14 +6318,14 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1932,
"failureCount": 1933,
"failureRate": 0.9284,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0716,
"total": 2081,
"total": 2082,
"unresolvedFailureCount": 1155
},
"Iluvatar_mrv-100": {
@@ -15344,6 +15344,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -40084,6 +40107,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -51432,20 +51479,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17067,
"totalRecords": 17288,
"terminalRecords": 17068,
"totalRecords": 17289,
"totals": {
"attributableFailureCount": 6115,
"attributableFailureCount": 6116,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7081,
"decisionTotal": 7082,
"failureBreakdown": {
"ambiguous_runtime": 4425,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2172,
"framework_architecture_unsupported": 2173,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 938,
@@ -51456,14 +51503,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16101,
"failureCount": 16102,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17067,
"total": 17068,
"unresolvedFailureCount": 9048
},
"warnings": [
@@ -51472,15 +51519,15 @@
"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 Iluvatar_bi-150 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。",
"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。",
@@ -51504,7 +51551,6 @@
"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。",
@@ -51518,10 +51564,11 @@
"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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17288,
"summarizedRecords": 17289,
"version": 1
}