Two papers accepted at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 24)

Two papers from our lab have been accepted by the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2024):

  • PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation. Accepted at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2024).
  • Static Generation of Efficient OpenMP Offload Data Mappings. Accepted at the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2024).