triton-inference-server/server

How to free multiple gpu memory

Open

#7,825 建立於 2024年11月22日

在 GitHub 查看
 (1 留言) (0 反應) (0 負責人)Python (1,304 fork)batch import
help wantedonnxquestion

倉庫指標

Star
 (6,593 star)
PR 合併指標
 (平均合併 2天 16小時) (30 天內合併 34 個 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 ]
    }
]

貢獻者指南