llm-d 1.0 hardens open-source AI inference for day 2 production operations
Release
Peter Hess
Blog
422 results for AI
The chips of tomorrow may well take inspiration from the architecture of our brains
ExplainerPeter HessThe next generation of AI for enterprise is here — don't take it for Granite
NewsMike MurphyThese new IBM agents will give developers new ways to solve problems — and clear their backlog
NewsMike MurphyAn air traffic controller for LLMs
ExplainerKim MartineauWhy we’re teaching LLMs to forget things
ExplainerKim MartineauNew algorithms open possibilities for training AI models on analog chips
ResearchPeter HessFor LLMs, IBM’s NorthPole chip overcomes the tradeoff between speed and efficiency
ResearchPeter HessHow memory augmentation can improve large language model efficiency and flexibility
ResearchPeter HessIntroducing Prithvi WxC, a new general-purpose AI model for weather and climate
NewsKim MartineauReinventing data preparation on cloud to scale enterprise AI
NewsMike MurphyTraining AI models faster than ever
NewsPeter HessHudson Forum 2024: Building the future with collaboration and math
NewsMike MurphySimplify your Code LLM solutions using CodeLLM DevKit
Technical noteRangeet Pan, Rahul Krishna, Saurabh Sinha, Raju Pavuluri, and Maja VukovicA toxic language filter built for speed
NewsKim MartineauHow IBM Research built a lab for the future of computing
Deep DiveMike MurphyImproving Hugging Face training efficiency through packing with flash attention
Technical noteRhui Dih Lee, Arthur Zucker, Achintya Kundu, Laura Wynter, Raghu Ganti, and Mayank Mishra
