oldcap

Posts

• Amazon's Exabyte-Scale Migration from Apache Spark to Ray (Saving $120M / Year)
  by oldcapon 7/25/2024, 5:58 PMwith 0 comments
• Uber's Journey from Predictive to Generative AI
  by oldcapon 5/3/2024, 5:11 PMwith 0 comments
• Loading LLM (Llama-2 70B) 20x faster with Anyscale Endpoints
  by oldcapon 10/13/2023, 2:48 PMwith 2 comments