Original ResearchPublished 4 June 2026SWEET: serving workload-balanced end-to-end efficient and tailored edge inference via quantization and partitioningXiangchen Li · Saeid Ghafouri · Hans Vandierendonck · Deepu John · Dimitrios S. NikolopoulosFrontiers in Complex Systemsdoi 10.3389/fcpxs.2026.1801157