3 papers
cs.DC2025
Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens
Yanpeng Yu, Haiyue Ma, Krish Agarwal +10
Expert Parallelism (EP) permits Mixture of Experts (MoE) models to scale beyond a single GPU. To address load imbalance across GPUs in EP, existing approaches aim to balance the nu…
cs.DC2024
PULSE: Accelerating Distributed Pointer-Traversals on Disaggregated Memory (Extended Version)
Yupeng Tang, Seung-seob Lee, Abhishek Bhattacharjee +1
Caches at CPU nodes in disaggregated memory architectures amortize the high data access latency over the network. However, such caches are fundamentally unable to improve performan…
cs.CL2024
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
In Gim, Guojun Chen, Seung-seob Lee +3
We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have ov…