Server deployment, parallel requests with continuous batching, new REST API endpoint, and refreshed application UI

Hacker News is a community-driven platform for sharing and discussing technology news, startups, and programming-related topics. Through user submissions and comments, Hacker News offers insights into emerging technology trends, industry developments, and entrepreneurial ventures. Readers can participate in discussions, share their insights, and stay informed about the latest advancements in technology and innovation.

Hacker News

LM Studio 0.4.0 introduces llmster, a headless daemon for server deployment without GUI dependencies. The release adds parallel request processing with continuous batching via llama.cpp 2.0.0, a new stateful /v1/chat REST API endpoint with MCP support, and permission key management. The desktop app receives a UI refresh with split view chat sessions, PDF/markdown export, developer mode, and improved CLI experience. Installation is available via curl/bash on Linux/Mac and PowerShell on Windows.

Introducing LM Studio 0.4.0