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

state: generation 18119 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 23:07:52 +00:00
parent c63df0be10
commit 3c888616c0
8 changed files with 1594 additions and 1548 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T21:58:57.842255+00:00",
"lastSyncTime": "2026-09-28T21:58:57.568298+00:00",
"generatedAt": "2026-09-28T23:06:29.026754+00:00",
"lastSyncTime": "2026-09-28T23:06:28.764950+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3864,25 +3864,25 @@
"decisionSuccessRate": 0.3636,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 43,
"framework_architecture_unsupported": 11,
"model_load": 3,
"platform_infrastructure": 1,
"参数/模板问题": 1,
"验证失败": 3
},
"failureCount": 61,
"failureRate": 0.8841,
"failureCount": 62,
"failureRate": 0.8857,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.1159,
"successRate": 0.1143,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 69,
"unresolvedFailureCount": 46
"total": 70,
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 25,
@@ -6034,7 +6034,7 @@
"decisionSuccessRate": 0.4167,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 90,
"ambiguous_runtime": 91,
"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": 126,
"failureRate": 0.863,
"failureCount": 127,
"failureRate": 0.8639,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 20,
"successRate": 0.137,
"total": 146,
"unresolvedFailureCount": 97
"successRate": 0.1361,
"total": 147,
"unresolvedFailureCount": 98
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 56,
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T21:58:57.829634+00:00",
"generatedAt": "2026-09-28T23:06:29.013975+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6245,7 +6245,7 @@
"decisionSuccessRate": 0.0891,
"decisionTotal": 819,
"failureBreakdown": {
"ambiguous_runtime": 507,
"ambiguous_runtime": 508,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 299,
@@ -6258,15 +6258,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1611,
"failureCount": 1612,
"failureRate": 0.9567,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 73,
"successRate": 0.0433,
"total": 1684,
"unresolvedFailureCount": 849
"total": 1685,
"unresolvedFailureCount": 850
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 60,
@@ -11241,6 +11241,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|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-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -34178,6 +34201,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|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-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -51997,15 +52044,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17088,
"totalRecords": 17309,
"terminalRecords": 17089,
"totalRecords": 17310,
"totals": {
"attributableFailureCount": 6126,
"decisionFailureRate": 0.8638,
"decisionSuccessRate": 0.1362,
"decisionTotal": 7092,
"failureBreakdown": {
"ambiguous_runtime": 4435,
"ambiguous_runtime": 4436,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -52021,15 +52068,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16122,
"failureCount": 16123,
"failureRate": 0.9435,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0565,
"total": 17088,
"unresolvedFailureCount": 9058
"total": 17089,
"unresolvedFailureCount": 9059
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -52058,7 +52105,6 @@
"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。",
@@ -52083,10 +52129,11 @@
"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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17309,
"summarizedRecords": 17310,
"version": 1
}