SwiftSpec: Disaggregated Speculative Decoding and Fused Kernels for Low-Latency LLM Inference
Open Access
- 22 March 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2197-2211
Abstract
No abstract availableFunding Information
- National Science Foundation (CCF-2119184)
- National Science Foundation (CNS-2313190)
- National Science Foundation (CCF-1822949)
- National Science Foundation (CNS-1956180)
This publication has 6 references indexed in Scilit:
- Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection2025
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation2024
- CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving2024
- FLTRNN: Faithful Long-Horizon Task Planning for Robotics with Large Language Models2024
- SpecInfer: Accelerating Large Language Model Serving with Tree-based Speculative Inference and Verification2024
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019