Showing cs.DCShow all
2 papers · 1 filter
cs.DC2026
Speculation at a Distance: Where Edge-Cloud Speculative Decoding Actually Pays Off
Yuan Lyu, Bharath Irukulapati, Jaya Prakash Champati
Speculative decoding (SD) accelerates LLM inference by - times when the draft and target models are co-located. This has motivated a distributed variant (DSD) that places t…
cs.DC2026
Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale
Tianci Bu, Yuan Lyu, Zixi Chen +6
Data-parallel (DP) load balancing has emerged as a first-order bottleneck in large-scale LLM serving. When a model is sharded across devices via tensor parallelism (TP) or expert p…