Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Spexis: Speculative Lookahead Scheduling for LLM Inference
Hyungyu Jung, Jaehyeok Yu, Hoonseo Choi +3
Spexis is a multi-GPU LLM inference framework that improves the efficiency of pipeline and tensor parallelism through speculative parallelism. Rather than using speculative decodin…
cs.LG2026
Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate
Jaemin Kim, Sungkyun Kim, Junyeol Lee +1
Large Language Models (LLMs) are widely used across many domains, but their scale makes deployment challenging. Post-Training Quantization (PTQ) reduces memory footprint without re…