triton-inference-server/server

How to free multiple gpu memory

Open

#7,825 创建于 2024年11月22日

在 GitHub 查看
 (1 评论) (0 反应) (0 负责人)Python (1,304 fork)batch import
help wantedonnxquestion

仓库指标

Star
 (6,593 star)
PR 合并指标
 (平均合并 2天 16小时) (30 天内合并 34 个 PR)

描述

The question is how do you free memory

https://github.com/triton-inference-server/onnxruntime_backend/issues/103

When the model is deployed to a single card, I can specify real-time release of gpu memory, but if the model is deployed to multiple cards, I don't know what the format looks like

parameters { key: "memory.enable_memory_arena_shrinkage" value: { string_value: "gpu:3" }  }

instance_group [
    {
        count: 1
        kind: KIND_GPU
        gpus: [ 3 ]
    }
]

贡献者指南