Presenter <Full Program · Contributors · Organizations · Search Program · Flagged · My Recommendations · Happening NowMore…Search ProgramFlaggedMy RecommendationsHappening NowMengdi WangInstitute of Computing Technology, Chinese Academy of SciencesPresentationsResearch ManuscriptTrimoe: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading11:50am - 12:03pm PDT Tuesday, July 28 Mtg Room 203ABDesignDES2B-I. In-memory and Near-memory Computing Architectures, Applications and Systems