# NetEase Games reduced LLM model load time to 3 minutes with Fluid prefetching

DevFeed: [NetEase Games reduced LLM model load time to 3 minutes with Fluid prefetching](<https://devfeed.tech/articles/how-netease-games-cut-llm-cold-starts-from-42-minutes-to-30-seconds-17636.md>)

Original publisher: [Read original article](<https://thenewstack.io/netease-fluid-llm-inference/>)

Author: Haifeng Liao

Published: 2026-05-06T13:00:00Z

Content type: article

Language: en

Sources: [Kubernetes Overview, News and Trends | The New Stack](<https://devfeed.tech/sources/kubernetes-overview-news-and-trends-the-new-stack.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI Inference](<https://devfeed.tech/topics/ai-inference.md>), [AI Platform](<https://devfeed.tech/topics/ai-platform.md>), [autoscaling](<https://devfeed.tech/topics/autoscaling.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [GPU](<https://devfeed.tech/topics/gpu.md>)

Tags: [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-platform](<https://devfeed.tech/tags/ai-platform.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [cache](<https://devfeed.tech/tags/cache.md>), [cncf](<https://devfeed.tech/tags/cncf.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [post-contributed](<https://devfeed.tech/tags/post-contributed.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [sponsor-cncf](<https://devfeed.tech/tags/sponsor-cncf.md>), [sponsored-post-contributed](<https://devfeed.tech/tags/sponsored-post-contributed.md>)

## AI overview

NetEase Games describes how slow model loading limited serverless LLM inference across regions. Using an Alluxio-based cache and then Fluid's prefetching workflow, the representative model load time fell from 42 minutes to 3 minutes.

## Source excerpt

At NetEase Games, we learned a hard lesson about large language model (LLM) inference in production: elastic compute is only The post How NetEase Games cut LLM cold starts from 42 minutes to 30 seconds appeared first on The New Stack.