pytorch/serve

Enabling HTTP caching of inference results

Open

#1,527 建立於 2022年3月23日

在 GitHub 查看
 (2 留言) (4 反應) (1 負責人)Java (3,844 star) (790 fork)batch import
enhancementhelp wanted

描述

Is your feature request related to a problem? Please describe.

Currently, TorchServe adds headers that prevent from caching the inference results: https://github.com/pytorch/serve/blob/30f83500b0850e26ec55581f48a9307b1986f9f9/frontend/server/src/main/java/org/pytorch/serve/util/NettyUtils.java#L187-L190

This prevents some reverse-proxies like nginx from caching the results

Describe the solution

It would be great to have a way to override this behavior, either from the model handler, or through some configuration key.

Describe alternatives solution

N/A

貢獻者指南

技術棧
javapython
領域
backendperformance
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
half day
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
JavaNettyTorchServe internalsHTTP caching concepts
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
40
研究方向
Investigate the file frontend/server/src/main/java/org/pytorch/serve/util/NettyUtils.java, specifically lines 187-190 where caching prevention headers are set. Consider adding a configuration option or model handler method to allow overriding these headers. Review existing configuration mechanisms in TorchServe to understand how to implement a toggle for caching. Look at discussions in the issue comments for any additional context or proposed solutions.