A Photonic-CXL Memory Appliance for Scalable KV Cache Management in LLM Inference

📅 2026-07-29
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the memory capacity and bandwidth limitations of KV caching in large language model inference, which hinder simultaneous support for terabyte-scale memory and hundreds of gigabytes per second throughput. The authors propose a novel optoelectronic hybrid CXL memory architecture that introduces passive optical interconnects into a CXL memory pool, enabling a switchless full-mesh topology that allows 16 hosts to share 32 TB of memory. By eliminating electrical switches, the design circumvents bottlenecks in latency, reach, and power consumption, yielding a scalable low-latency shared memory system. Experimental results demonstrate over 50% lower system latency compared to an all-electrical CXL baseline and a 6.6× speedup in first-token generation time under multi-turn dialogue scenarios, effectively mitigating the performance cliff caused by cache eviction.
📝 Abstract
LLM inference at scale faces a memory wall. The KV cache demands tens of terabytes at hundreds of gigabytes per second, yet no current memory tier delivers both at once. Characterization across multi-generation GPU systems with various LLaMA models shows host memory retrieval achieves up to 100x speedup over re-computation but supports only tens of concurrent long-context users. Electrical CXL pooling theoretically bridges this gap, but switch latency, cable reach limits, and power-scaling issues prevent practical TB-scale deployments. We present the Marvell Photonic Fabric Memory Appliance, a photonic-CXL hybrid architecture replacing electrical switches with a passive fiber shuffle to deliver 32 TB shared memory across 16 hosts via a switch-free full- crossbar topology. Emulation results demonstrate over 50 percent latency reduction versus electrical CXL pools. Simulation results show that the PF Memory Appliance eliminates cache eviction cliffs by improving time-to-first-token by 6.6x for multi-turn conversations workloads.
Problem

Research questions and friction points this paper is trying to address.

LLM inference
KV cache
memory wall
CXL
scalability
Innovation

Methods, ideas, or system contributions that make the work stand out.

Photonic-CXL
KV cache
Memory disaggregation
Full-crossbar topology
LLM inference
🔎 Similar Papers
J
Jing Ding
Machine Learning, Marvell Technology, Santa Clara, USA
Y
Yash Nishant
Machine Learning, Marvell Technology, Santa Clara, USA
C
Chandrish Ambati
Machine Learning, Marvell Technology, Santa Clara, USA
J
Jyothsna Kamati
Design Verification, Marvell Technology, Santa Clara, USA
T
Trung Diep
Machine Learning, Marvell Technology, Santa Clara, USA