We have 3 of 155 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.
Mobile vendors and application developers increasingly deploy LLMs on smartphones for diverse prefill-only services. Yet current systems rely mainly on dense models whose regular computation maps efficiently to mobile NPUs, leaving more capable MoEs underused. MoE prefill does not fit mobile NPUs: NPU graphs are fixed...
This work investigates the design of two-stage auctions that allow advertisers to submit and update their bids, with second-stage bids serving as refinements of the initial ones, and proposes a dynamic two-stage auction that adopts realization-dependent entry fees with discounts.
This work proposes a series of optimizations for these two kernels, including computation-transfer pipelining, load balancing, and memory access fusion, achieving 1.97 × to 2.16 × proof generation speedup over a state-of-the-art open source GPU acceleration library.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
