collaborators

11 papers

cs.LG2026

HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval

Omin Kwon, Doyeon Kim, Jongseok Park +3

The KV cache dominates GPU memory in long-context LLM serving, crowding out batch capacity and leaving GPU compute idle. Offloading the cache to CPU DRAM restores capacity, but the…

cs.AI2026

Qrita: High-performance Top-k and Top-p using Pivot-based Truncation and Selection

Jongseok Park, Sunga Kim, Alvin Cheung +1

Despite their importance in model sampling, efficient implementation of Top-k and Top-p algorithms for large vocabularies remains a significant challenge. Existing approaches often…

cs.LG2026

Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution

Jongseok Park, Sunga Kim, Zhenyu Gu +2

Mixture of Experts (MoE) architecture has become the standard for state-of-the-art large language models, owing to its computational efficiency through sparse expert activation. Ho…

cs.DC2026

Unleashing Scalable Context Parallelism for Foundation Models Pre-Training via FCP

Yilong Zhao, Xiaonan Nie, Kan Zhu +6

Context parallelism (CP) has been widely adopted to support the growing context length in foundation model pretraining. However, existing designs fail to handle the large variation…

cs.CL2026

Speculative Decoding: Performance or Illusion?

Xiaoxuan Liu, Jiaxiang Yu, Jongseok Park +2

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations r…

cs.AI2026

: Faster Test-Time Scaling through Speculative Drafts

Mert Cemri, Nived Rajaraman, Rishabh Tiwari +6

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thor…