3 papers
cs.LG2026
A Practical Investigation of Training-free Relaxed Speculative Decoding
Guoxuan Xia, Luka Ribar, Paul Balanca
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard spec…
cs.LG2026
MXNorm: Reusing MXFP block scales for efficient tensor normalisation
Callum McLean, Luke Y. Prince, Alexandre Payot +2
Matrix multiplication performance has long been the major bottleneck to scaling deep learning workloads, which has stimulated the design of new accelerators that use increasingly l…
cs.LG2025
Elucidating the Design Space of FP4 training
Robert Hu, Carlo Luschi, Paul Balanca
The increasing computational demands of foundation models have spurred research into low-precision training, with 4-bit floating-point (\texttt{FP4}) formats emerging as a frontier…