Tag : LLM
Posts tagged with 'LLM'
Building Production RAG Systems: Lessons from Tariff Support
By Sergey LeksikovLablup's research team shares lessons from two production RAG systems, the HSense tariff classifier (92.4% Top-1) and a Backend.AI support assistant, including why retrieval quality matters more than model choice.23 April 2026
The Pulse of 500+ GPUs: Monitoring Large-Scale AI Training Clusters
By Hanjeong LeeHow Lablup built proactive fault detection for a 500+ NVIDIA B200 GPU cluster while supporting Solar Open 102B pretraining, including its data collection and real anomaly cases.20 February 2026
Behind Lablup x Upstage's Phase 1 Win for the Sovereign AI Foundation Model Project
By LablupThe Upstage consortium, with Lablup as infrastructure partner, passed Phase 1 of Korea's Sovereign AI Foundation Model program. Team members share the behind-the-scenes story.6 February 2026
Inside Lablup’s AI Hackathon 'Idea | up'
By Juyoung LimOur recent internal hackathon at Lablup was a chance to put this intuition to the test. It wasn’t just about development—teams from research, sales, finance, and developer relations all came together. Each group defined their own problems in their own language and set out to design unique AI-powered tools. It was a collective experiment in rethinking how we approach challenges and leverage AI, regardless of our backgrounds or roles.14 July 2025
Recap of Yonggeun's Lablup Internship, 2nd half 2024
By Yonggeun KwonAs part of Lablup's internship program, Yonggeun Kwon has spent the last six months developing domain-adaptive language models and evaluating Helmsman LLM-based agents for simplifying CLI commands. He describes his experience at Lablup as “meaningful,” and has had the opportunity to present at both Pycon and Lablup conferences during his internship.27 January 2025
Developing KIMCHI: An AI Image Generation Model Reflecting Korean Culture
By Yonggeun KwonMeet KIMCHI, a fine-tuned diffusion model that understands Korean prompts natively and generates culturally authentic images, outperforming DALL-E 3 and Stable Diffusion on cultural alignment.26 December 2024
Model Variant: Serving Multiple Models with Ease
By Jihyun KangA look at the enhanced model service in Backend.AI 23.09, which makes it easy to serve many models, not just one.11 July 2024
![[Featured articles] Scale entanglement](/_next/image?url=https%3A%2F%2Fcdn.lablup.com%2Fscale_entanglement_8b2596633c.jpg&w=2048&q=75)
[Featured articles] Scale entanglement
By Jeongkyu Shin25 March 2024
