Decoding methods

  1. Economic conditions and presidential approval move together in patterned ways
    Machine learning analysis identifies which macroeconomic conditions drive presidential approval ratings. Public sector activity, recession timing, and housing markets show distinct temporal dynamics.
  2. CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving
    System offloads key-value caches to remote FPGA memory using CXL interconnects, achieving 3.2× throughput gains and 2.8× memory cost reduction for datacenter LLM serving.
  3. PAT: Accelerating LLM Decoding via P refix- A ware A t tention with Resource Efficient Multi-Tile Kernel
    PAT optimizes LLM decode-phase attention by exploiting shared request prefixes and adaptive kernel tiling, reducing memory bandwidth bottlenecks in multi-request serving scenarios.