3 papers
cs.CL2025
Cacheback: Speculative Decoding With Nothing But Cache
Zhiyao Ma, In Gim, Lin Zhong
We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) infere…
cs.CL2025
Serve Programs, Not Prompts
In Gim, Lin Zhong
Current large language model (LLM) serving systems, primarily designed for text completion, are neither efficient nor adaptable for increasingly complex LLM applications due to the…
cs.CL2025
Pie: A Programmable Serving System for Emerging LLM Applications
In Gim, Zhiyao Ma, Seung-seob Lee +1
Emerging large language model (LLM) applications involve diverse reasoning strategies and agentic workflows, straining the capabilities of existing serving systems built on a monol…