Skip to content

批量推理vllm,出现repetition现象 #7394

@Redamency

Description

@Redamency

多卡批量推理 swift infer 时,推理后端选择vllm,推理的response会出现较多的repetition,推理后端换成pt,推理的response不会出现repetition

下面是我的infer脚本
NPROC_PER_NODE=4 CUDA_VISIBLE_DEVICES=0,1,2,3 swift infer
--model ./output/dpo/v9-20260114-161202/checkpoint-100
--infer_backend vllm
--val_dataset ./data/dpo/val_1k_4_1.jsonl
--max_batch_size 32
--max_new_tokens 2048
--max_length 4096
--dataset_num_proc 4 \

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions