---
format: "aidr-story-markdown/v1"
id: "bcb7aae5f14dbfc1609e36afc927f586926b34f3d1528aee837d13e86ec89188"
canonical_url: "https://aidr.today/bcb7aae5?lang=en"
title: "Liquid AI Launches RIPL, a Real-Time Inference Engine for Sub-50 ms LFMs"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-22T17:33:25.000Z"
category: "Frameworks"
topics: ["inference","framework"]
source_urls: ["https://www.marktechpost.com/2026/10/22/liquid-ai-ripl-real-time-inference-engine/"]
summary: "Liquid AI released RIPL, a real-time inference engine for its LFM models. On one B200, LFM2.5-1.2B on RIPL showed 14.4 to 28.4x lower p95 latency than Qwen3.5-0.8B on vLLM."
---

# Liquid AI Launches RIPL, a Real\-Time Inference Engine for Sub\-50 ms LFMs

> [Open the canonical story](<https://aidr.today/bcb7aae5?lang=en>)

**Published:** 2026-10-22T17:33:25.000Z
**Category:** Frameworks
**Topics:** inference, framework

## Summary

Liquid AI released RIPL, a real\-time inference engine for its LFM models\. On one B200, LFM2\.5\-1\.2B on RIPL showed 14\.4 to 28\.4x lower p95 latency than Qwen3\.5\-0\.8B on vLLM\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/10/22/liquid-ai-ripl-real-time-inference-engine/>)