arXiv AI By Chendong Song, Meixuan Wang, Hang Zhou, Hong Liang, Yuan Lyu, Zixi Chen, Yuwei Fan, Zijie Zhou

Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads

Read the original on arXiv AI →

arXiv:2601. 21351v4 Announce Type: replace-cross Abstract: Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensive FFN computation, connected by per-step communication.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Aug 5

AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation

Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language models. While existing AFD systems improve the efficiency of disaggregated execution, they leave a deployment question unanswered: under the same model, workload, time-per-output-token (TPOT) service-level objective (SLO), hardware budget, hardware catalog, and runtime capabilities, does AFD provide higher throughput than the best collocated deployment?