---
format: "aidr-story-markdown/v1"
id: "e21378f22db2cf2557909666ade5eec393b3c706679e975980ea513b95054da3"
canonical_url: "https://aidr.today/e21378f2?lang=en"
title: "WebLLM: high-performance in-browser LLM inference engine"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-02T14:02:35.000Z"
category: "Infra"
topics: ["llm","inference","open-source"]
source_urls: ["https://github.com/mlc-ai/web-llm","https://news.ycombinator.com/item?id=49536411"]
summary: "High-performance In-browser LLM Inference Engine . Contribute to mlc-ai/web-llm development by creating an account on GitHub."
---

# WebLLM: high\-performance in\-browser LLM inference engine

> [Open the canonical story](<https://aidr.today/e21378f2?lang=en>)

**Published:** 2026-09-02T14:02:35.000Z
**Category:** Infra
**Topics:** llm, inference, open\-source

## Summary

High\-performance In\-browser LLM Inference Engine \. Contribute to mlc\-ai/web\-llm development by creating an account on GitHub\.

## Sources

- [Story source](<https://github.com/mlc-ai/web-llm>)
- [Discussion](<https://news.ycombinator.com/item?id=49536411>)