We have 5 of 16 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Simulations demonstrate that TopoCompress effectively reduces cross-server traffic and deployment resource consumption while maintaining controllable inference quality, enabling efficient distributed MoE inference over bandwidth- and resource-constrained edge infrastructures.
A communication-aware adaptive-depth framework is proposed in this paper, termed TrimMoE, which couples layer skipping and confidence-based early exit with substitute execution and server-expert selection under a unified quality budget and proves that the substitution-and-skipping proxy degradation never exceeds the co...
A similarity-aware expert allocation and distributed deployment framework, dubbed OrderMoE, which aims to accelerate edge MoE inference while balancing inference latency, communication overhead, server workload, and inference quality.
HetRoute introduces a unified per-assignment cost model that explicitly captures four cost components: cross-server transmission, GPU-CPU offloading, GPU computation with queueing, and quantization-induced quality penalty and establishes fallback feasibility, a bound on the number of participating servers, per-layer op...
SPICE is presented, a speculative prefetching framework for MoE offloading that combines lightweight expert prediction with confidence-aware CPU-GPU orchestration and achieves up to 3.12 speedup in Time Per Output Token (TPOT) with minimal quality loss, showing that effective MoE offloading requires not only predicting...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
