2 papers
cs.LG2026
HERALD: High-Throughput Block Diffusion LLM Inference via CPU-GPU Cooperative KV Cache Retrieval
Omin Kwon, Doyeon Kim, Jongseok Park +4
Block diffusion LLMs (block dLLMs) improve decode throughput by generating tokens in parallel, and are emerging as a next-generation alternative to autoregressive LLMs. At long con…
cs.LG2026
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…