Tag: Networks & Cloud Computing
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.
.plan-26-10: Streaming TESSERA working, biodiversity action papers, and FPL takes off
Browser-based streaming interface for satellite embeddings demonstrates client-side geospatial analysis, raising programming paradigm questions for Earth observation workflows.
