7 papers
Speculative Decoding: Performance or Illusion?
Xiaoxuan Liu, Jiaxiang Yu, Jongseok Park +2
Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations r…
TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
Xiaoxuan Liu, Jongseok Park, Langxiang Hu +10
Large Language Model (LLM) serving systems batch concurrent user requests to achieve efficient serving. However, in real-world deployments, such inter-request parallelism from batc…
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
Kuntai Du, Bowen Wang, Chen Zhang +9
Besides typical generative applications, like ChatGPT, GitHub Copilot, and Cursor, we observe an emerging trend that LLMs are increasingly used in traditional discriminative tasks,…
Jenga: Effective Memory Management for Serving LLM with Heterogeneity
Chen Zhang, Kuntai Du, Shu Liu +10
Large language models (LLMs) are widely used but expensive to run, especially as inference workloads grow. To lower costs, maximizing the request batch size by managing GPU memory…
MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs
Shiyi Cao, Shu Liu, Tyler Griggs +6
Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of comp…
Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity
Tyler Griggs, Xiaoxuan Liu, Jiaxiang Yu +4
Large language models (LLMs) are increasingly integrated into many online services, yet they remain cost-prohibitive to deploy due to the requirement of expensive GPU instances. Pr…