---
title: "Discussion on \"I Built a Prefix-Cache-Aware LLM Gateway in Go — And Reduced TTFT by 90%\" | Hashnode"
description: "Discussion on \"I Built a Prefix-Cache-Aware LLM Gateway in Go — And Reduced TTFT by 90%\". Prefix-Cache-Aware LLM Gateway in Go — And Reduced TTFT by 90%"
url: "https://hashnode.com/posts/i-built-a-prefix-cache-aware-llm-gateway-in-go-and-reduced-ttft-by-90/6abd664270f248d48a587ea9"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [I Built a Prefix-Cache-Aware LLM Gateway in Go — And Reduced TTFT by 90%](https://aekshant.hashnode.dev/i-built-a-prefix-cache-aware-llm-gateway-in-go-and-reduced-ttft-by-90?utm_source=hashnode&utm_medium=feed)

Prefix-Cache-Aware LLM Gateway in Go — And Reduced TTFT by 90%

Sep 30 · 4 min read · aekshant.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#inference](https://hashnode.com/tag/inference)
-   [#ai-gateway](https://hashnode.com/tag/ai-gateway)
-   [#platform-engineering](https://hashnode.com/tag/platform-engineering)
-   [#ai-platform](https://hashnode.com/tag/ai-platform)

## Written by

[kalyan dahake](https://hashnode.com/@kalyandahake)

@kalyandahake · India

  
[View profile](https://hashnode.com/@kalyandahake)

Tech Enthusiast

I'm building systems across industries, ensuring seamless software delivery. I manage everything from system design to deployment, driving operational excellence and client satisfaction.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.