Categories

By MTC Team

• LightLLM v1.0.0--Minimal Inter-Process Communication Overhead, Fastest DeepSeek-R1 Serving Performance on Single H200, and Prototype Support for PD-Disaggregation

  By MTC Team  · 16 Feb 2025

  We are delighted to announce the release of LightLLM v1.0.0.

• Reducing Overhead with Cuda Graph

  By MTC Team  · 22 Jan 2025

  Cuda Graph is used to reduce overhead in LightLLM.