vllm/model_executor/models/qwen2.py · ec0136e77cfe71a509c365309e60e3d110fdaa37 · OpenDAS / vllm_cscc · GitLab

Find file Blame History Permalink

1.解决qwen lora模型推理结果异常问题 · da39222e
王敏 authored Dec 23, 2024
```
2.修复medusa推理时内存访问越界问题
3.benchmark_moe添加deepseek_v2模型
```
da39222e

qwen2.py 22.4 KB