Despite the success of large language models (LLMs) as general-purpose AI tools, their high demand for computational resources make their deployment challenging in many real-world scenarios. The sizes of the model and conversation state are limited by the available high-bandwidth memory, limiting the number of users that can be served and the maximum conversation length. At present…
]]>Every year, as part of their coursework, students from the University of Warsaw, Poland get to work under the supervision of engineers from the NVIDIA Warsaw office on challenging problems in deep learning and accelerated computing. We present the work of three M.Sc. students—Alicja Ziarko, Pawe? Pawlik, and Micha? Siennicki—who managed to significantly reduce the latency in TorToiSe…
]]>