BLOG

Welcome to the Eigen AI blog! Here, you will find commentaries, news, and updates on our latest research projects and progress in the field of efficient generative AI.

Day 0 Support of Serving OpenAI GPT-OSS on Hopper and Blackwell GPUs with Free Online Playground

by: Eigen AI Team, 08 Aug, 2025

In this blog, we're excited to achieve day 0 support for the serving of OpenAI’s GPT-OSS-120B and GPT-OSS-20B on Hopper/Blackwell GPUs in collaboration with the SGLang team. We also introduce a free online playground featuring both web and API access to the GPT-OSS-120B model (chat.eigenai.com) in p...

Accelerating SGLang with Multiple Token Prediction

by: Eigen AI and SGLang Teams, 16 Jul, 2025

Eigen AI collaborates with SGLang to support smooth combination of these advanced features: Multiple Token Prediction (MTP), Large-Scale Expert Parallelism (EP), and Prefill-Decode disaggregation.

WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning

by: Eigen AI Team, 27 May, 2025

Eigen AI introduces WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style RL framework designed to enhance single-step reasoning and planning for business-oriented web navigation.