2 papers
cs.AR2025
Splitwiser: Efficient LM inference with constrained resources
Asad Aali, Adney Cardoza, Melissa Capo
Efficient inference of LLMs remains a crucial challenge, with two main phases: a compute-intensive prompt computation and a memory-intensive token generation. Despite existing batc…
cs.DC2020
Fault-tolerant and Transactional Stateful Serverless Workflows (extended version)
Haoran Zhang, Adney Cardoza, Peter Baile Chen +2
This paper introduces Beldi, a library and runtime system for writing and composing fault-tolerant and transactional stateful serverless functions. Beldi runs on existing providers…