7 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…
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…
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
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 (…
Binary Neural Networks for Large Language Model: A Survey
Liangdong Liu, Zhitong Zheng, Cong Wang +2
Large language models (LLMs) have wide applications in the field of natural language processing(NLP), such as GPT-4 and Llama. However, with the exponential growth of model paramet…
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…