Latest in Boss Personally

Sort by

285 items

Simplismart supercharges AI performance with personalized, software-optimized inference engine

The software-optimized inference engine behind Simiplismart MLOps platform runs Llama3.1 8B at a peak throughput of 501 tokens per second.
Tech - VentureBeat - October 17
My top 10: Jackie Wullschläger’s personal pick of Venice’s Accademia Gallery

The FT’s art critic’s guide to navigating a world-class permanent collection spanning the 14th to 19th centuries
World - Financial Times - October 18

Simplismart supercharges AI performance with personalized, software-optimized inference engine