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

state: generation 17873 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 12:17:59 +00:00
parent 597b959b1a
commit a6efd8a34f
8 changed files with 1716 additions and 1670 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T11:49:33.080031+00:00",
"lastSyncTime": "2026-09-28T11:49:32.855663+00:00",
"generatedAt": "2026-09-28T12:16:36.344733+00:00",
"lastSyncTime": "2026-09-28T12:16:36.062761+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3987,24 +3987,24 @@
"decisionSuccessRate": 0.4615,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 47,
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 11,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 64,
"failureRate": 0.8421,
"failureCount": 65,
"failureRate": 0.8442,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.1579,
"successRate": 0.1558,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 76,
"unresolvedFailureCount": 50
"total": 77,
"unresolvedFailureCount": 51
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 22,
@@ -6034,7 +6034,7 @@
"decisionSuccessRate": 0.4167,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 88,
"ambiguous_runtime": 89,
"framework_architecture_unsupported": 22,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6042,15 +6042,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 124,
"failureRate": 0.8611,
"failureCount": 125,
"failureRate": 0.8621,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 20,
"successRate": 0.1389,
"total": 144,
"unresolvedFailureCount": 95
"successRate": 0.1379,
"total": 145,
"unresolvedFailureCount": 96
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 55,
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T11:49:33.067040+00:00",
"generatedAt": "2026-09-28T12:16:36.331263+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6274,7 +6274,7 @@
"decisionSuccessRate": 0.1892,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 151,
"ambiguous_runtime": 152,
"framework_architecture_unsupported": 48,
"memory_capacity": 4,
"model_load": 5,
@@ -6283,15 +6283,15 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 276,
"failureRate": 0.9517,
"failureCount": 277,
"failureRate": 0.9519,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 14,
"successRate": 0.0483,
"total": 290,
"unresolvedFailureCount": 214
"successRate": 0.0481,
"total": 291,
"unresolvedFailureCount": 215
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -13176,6 +13176,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
"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|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -37203,6 +37226,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"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|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -51807,15 +51854,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17077,
"totalRecords": 17298,
"terminalRecords": 17078,
"totalRecords": 17299,
"totals": {
"attributableFailureCount": 6123,
"decisionFailureRate": 0.8637,
"decisionSuccessRate": 0.1363,
"decisionTotal": 7089,
"failureBreakdown": {
"ambiguous_runtime": 4427,
"ambiguous_runtime": 4428,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -51831,15 +51878,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16111,
"failureCount": 16112,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17077,
"unresolvedFailureCount": 9050
"total": 17078,
"unresolvedFailureCount": 9051
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -51868,6 +51915,7 @@
"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 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 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 Kunlunxin_p-800|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 MetaX_c-500|vllm|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 Ascend_910-b4|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|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51892,11 +51940,10 @@
"组合 hygon_k100-ai|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 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 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 Vastai_va16|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|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|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": 17298,
"summarizedRecords": 17299,
"version": 1
}