2025

March 02, 2025 Test-time Compute Algorithms for Diffusion Language Models
February 25, 2025 A Distributed Inference Engine for SmolLM with Rust and gRPC
January 01, 2025 RL for Training Multiple Decoding Heads -- An Inference Acceleration Method in Language Models (ICLR 2025 Workshop on Sparsity in LLMs)