Poster · Sydney
Keep or Preempt? Termination-Aware Scheduling for LLM Serving with Speculative Decoding
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Ziyu Cheng, Songtao Guo, Mingyan Li, Chang Han, Hongyu Xu, Xu Luo
- Organisations
- Chongqing University
- QRS classification
- Language models