6 papers
Rethinking Unified Memory for NPU-PIM Systems: Dual-View Memory for Dynamic Inference of LLM
Shixin Zhao, Lian Liu, Tianhua Han +3
Heterogeneous architectures that combine neural processing unit (NPU) and processing-in-memory (PIM) are increasingly adopted to accelerate LLM inference. Prior work focuses on bui…
Ouroboros: Wafer-Scale SRAM CIM with Token-Grained Pipelining for Large Language Model Inference
Yiqi Liu, Yudong Pan, Mengdi Wang +5
Conventional LLM inference architectures suffer from high energy and latency due to frequent data movement across memory hierarchies. We propose Ouroboros, a wafer-scale SRAM-based…
TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading
Yudong Pan, Yintao He, Tianhua Han +7
To deploy large Mixture-of-Experts (MoE) models cost-effectively, offloading-based single-GPU heterogeneous inference is crucial. While GPU-CPU architectures that offload cold expe…
PAM: Processing Across Memory Hierarchy for Efficient KV-centric LLM Serving System
Lian Liu, Shixin Zhao, Yutian Zhou +4
The widespread adoption of Large Language Models (LLMs) has exponentially increased the demand for efficient serving systems. With growing requests and context lengths, key-value (…
Be CIM or Be Memory: A Dual-mode-aware DNN Compiler for CIM Accelerators
Shixin Zhao, Yuming Li, Bing Li +4
Computing-in-memory (CIM) architectures demonstrate superior performance over traditional architectures. To unleash the potential of CIM accelerators, many compilation methods have…
Make LLM Inference Affordable to Everyone: Augmenting GPU Memory with NDP-DIMM
Lian Liu, Shixin Zhao, Bing Li +6
The billion-scale Large Language Models (LLMs) need deployment on expensive server-grade GPUs with large-storage HBMs and abundant computation capability. As LLM-assisted services…