Yongpan Liu

Latest

• Argus: Hardware-Software Co-Scaling of Tensor Parallelism for Efficient LLM Training
• Uncovering Contention-Based Side-Channel Threats in AMD Zen Chiplet Architectures
• HybridSpec: Exploiting Hybrid-bonding Memory to Accelerate LLM Serving through Heterogeneous Architecture and Speculative Decoding
• Hecaton: Training Large Language Models with Scalable Chiplet Systems