4 papers
MonoMoE: An Efficient Fused Mega-kernel for Quantized MoE Decoding
Yu Gong, Kailash Budhathoki, Taeho Kim +2
Mixture-of-Experts (MoE) layers increase model capacity without proportionally increasing arithmetic, but their sparse expert computation is difficult to execute efficiently during…
KernelSight-LM: A Kernel-Level LLM Inference Simulator
Xiteng Yao, Taeho Kim, Hengzhi Pei +7
As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to m…
XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
Daniil Vankov, Nikita Ivkin, Kyle Ulrich +3
Mixture-of-Experts (MoE) architectures are increasingly used to efficiently scale large language models. However, in production inference, request batching and speculative decoding…
When LLMs get significantly worse: A statistical approach to detect model degradations
Jonas Kübler, Kailash Budhathoki, Matthäus Kleindessner +4
Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others with…