5 papers
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…
MAGE: All-[MASK] Block Already Knows Where to Look in Block Diffusion LLM
Omin Kwon, Yeonjae Kim, Doyeon Kim +3
Block diffusion LLMs are an emerging paradigm for parallel language generation, but their KV caching makes memory access the dominant bottleneck in long-context inference. Sparse a…
NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs
Haeun Lee, Omin Kwon, Yeonhong Park +1
Meeting service-level objectives (SLOs) in Large Language Models (LLMs) serving is critical, but managing the high variability in load presents a significant challenge. Recent adva…
DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment
Sangwoo Kwon, Seong Hoon Seo, Jae W. Lee +1
How can we effectively handle queries for on-device large language models (LLMs) with varying runtime constraints, such as latency and accuracy? Multi-scale quantization addresses…
DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization
Yeonhong Park, Jake Hyun, Hojoon Kim +1
Quantization of Large Language Models (LLMs) has recently gained popularity, particularly for on-device settings with limited hardware resources. While efficient, quantization inev…