Lattice AI Research

Research focus

Architecture Design (Transformers, SSMs, MoE) (2)Distributed Systems & Hardware (2)Natural Language Processing (1)Inference & Quantization (1)

Frequent co-authors

Sang-Won Lee (2)Alish Kanani (1)Jaehyun Park (1)Umit Ogras (1)

Papers (2)

Aug 19, 2026

Jiahao Lin +45d ago·also Thanks:

HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads

Achieving up to 2.3x throughput gains, HYDRA reveals that co-designing architecture and runtime policies is essential for optimizing hybrid LLM workloads on chiplet systems.

Jiahao Lin, Alish Kanani, Sang-Won Lee +2

Architecture Design (Transformers, SSMs, MoE)Distributed Systems & Hardware Natural Language Processing

Mar 16, 2026

DUET: Disaggregated Hybrid Mamba-Transformer LLMs with Prefill and Decode-Specific Packages

Hybrid Mamba-Transformer models can get 4x faster time to first token and 1.4x higher throughput by disaggregating prefill and decode phases onto specialized accelerator packages.

Alish Kanani, Sangwan Lee, Sang-Won Lee +5

Architecture Design (Transformers, SSMs, MoE)Distributed Systems & Hardware Inference & Quantization

Search

Jiahao Lin

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)