3 papers
cs.AR2026
End-to-End Transformer Acceleration Through Processing-in-Memory Architectures
Xiaoxuan Yang, Peilin Chen, Tergel Molom-Ochir +1
Transformers have become central to natural language processing and large language models, but their deployment at scale faces three major challenges. First, the attention mechanis…
cs.AR2025
Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration
Peilin Chen, Xiaoxuan Yang
Large language models (LLMs) have gained great success in various domains. Existing systems cache Key and Value within the attention block to avoid redundant computations. However,…
cs.AR2025
Optimizing and Exploring System Performance in Compact Processing-in-Memory-based Chips
Peilin Chen, Xiaoxuan Yang
Processing-in-memory (PIM) is a promising computing paradigm to tackle the "memory wall" challenge. However, PIM system-level benefits over traditional von Neumann architecture can…