{"slug": "liquid-ai-launches-ripl-a-real-time-inference-engine-for-sub-50-ms-lfms", "title": "Liquid AI Launches RIPL, a Real-Time Inference Engine for Sub-50 ms LFMs", "summary": "Liquid AI released RIPL, a real-time inference engine for its LFM models, reporting that LFM2.5-1.2B running on RIPL achieved 14.4 to 28.4x lower p95 latency than Qwen3.5-0.8B on vLLM on a single B200 GPU. The engine targets sub-50 ms inference for Liquid AI's LFM models. The comparison matters for developers weighing serving stacks for low-latency language model deployments.", "body_md": "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.\n\nThe post [Liquid AI Launches RIPL, a Real-Time Inference Engine for Sub-50 ms LFMs](https://www.marktechpost.com/2026/10/22/liquid-ai-ripl-real-time-inference-engine/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/liquid-ai-launches-ripl-a-real-time-inference-engine-for-sub-50-ms-lfms", "canonical_source": "https://www.marktechpost.com/2026/10/22/liquid-ai-ripl-real-time-inference-engine/", "published_at": "2026-10-22 17:33:25+00:00", "updated_at": "2026-10-22 18:44:35.685522+00:00", "lang": "en", "topics": ["ai-infrastructure", "large-language-models", "ai-tools", "machine-learning"], "entities": ["Liquid AI", "RIPL", "LFM2.5-1.2B", "Qwen3.5-0.8B", "vLLM", "B200"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/liquid-ai-launches-ripl-a-real-time-inference-engine-for-sub-50-ms-lfms", "markdown": "https://wpnews.pro/news/liquid-ai-launches-ripl-a-real-time-inference-engine-for-sub-50-ms-lfms.md", "text": "https://wpnews.pro/news/liquid-ai-launches-ripl-a-real-time-inference-engine-for-sub-50-ms-lfms.txt", "jsonld": "https://wpnews.pro/news/liquid-ai-launches-ripl-a-real-time-inference-engine-for-sub-50-ms-lfms.jsonld"}}