We have 3 of 44 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.
C cumulative ablations show that adding the three mechanisms successively increases geometric-mean throughput, while budget adjustment improves accepted-token retention, and DScale is presented, preserving drafter architecture, weights, and full draft length.
Inspired by the brownout paradigm in service computing, BrownoutMoE reorganizes experts into groups to improve utilization and system efficiency while maintaining service quality and introduces a grouping-consistent distillation process to produce deployable models that are compatible with standard inference pipelines.
CoScale is proposed, a layer-wise dynamic scaling mechanism that selectively expands the parallelism of hot layers onto idle resources reclaimed from underutilized devices, enabling elastic data parallelism without altering model architectures or adding hardware overhead.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
