Poster · Sydney
Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Quan Nguyen-Tri, Mukul Ranjan, Zhiqiang Shen
- Organisations
- Mohamed bin Zayed University of Artificial Intelligence, Cornell University
- QRS classification
- Language models, Generative models, Efficient and distributed ML systems