2 papers
cs.DC2026
MANTA: Machine Learning Augmented Tiering Advisor
Johannes Freischuetz, Kiet Pham, Sujay Yadalam +3
Memory tiering has been used to expand memory capacity, particularly in datacenters, by combining fast DRAM with slower tiers, including CXL-attached memory. Its effectiveness depe…
cs.LG2026
TeDiServe: High SLO Attainment Serving for Diffusion Language Models
Tzu-Tao Chang, Benjamin Yuanyang Hong, Kiet Pham +1
Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during e…