IBM ResearchLabo·en·il y a 2 jours·via RSSA new plugin can enable fast runtime monitoring and controlresearch.ibm.comIBM Research·il y a 2 jours·research.ibm.comil y a 2 joursA new plugin can enable fast runtime monitoring and controlIBM's vLLM-Hook MIA lets developers inspect and edit the AI generation process with hardly any delay.
IBM ResearchLabo·en·il y a 3 jours·via RSSllm-d 1.0 hardens open-source AI inference for productionresearch.ibm.comIBM Research·il y a 3 jours·research.ibm.comil y a 3 joursllm-d 1.0 hardens open-source AI inference for productionThe distributed inference framework makes serving large models on your own infrastructure reliable and affordable for the agentic era.
IBM ResearchLabo·en·il y a 4 jours·via RSSNew course teaches how AI models run on modern acceleratorsresearch.ibm.comIBM Research·il y a 4 jours·research.ibm.comil y a 4 joursNew course teaches how AI models run on modern accelerators'Dataflow Architectures for AI' is a 6-course specialization from IBM Research that compares leading accelerator architectures through hands-on labs.
IBM ResearchLabo·en·il y a 10 jours·via RSSScaling AI-driven chip design with open agent factoriesresearch.ibm.comIBM Research·il y a 10 jours·research.ibm.comil y a 10 joursScaling AI-driven chip design with open agent factoriesOpen models and llm-d enabled IBM Research to explore quantum error correction hardware at 11.5× lower inference cost than an all-proprietary configuration.
IBM ResearchLabo·en·il y a 11 jours·via RSSHow distributed inference keeps large AI models movingresearch.ibm.comIBM Research·il y a 11 jours·research.ibm.comil y a 11 joursHow distributed inference keeps large AI models movingDistributed inference serving is an air traffic control tower for AI traffic, and agentic workflows make it more necessary than ever.
IBM ResearchLabo·en·il y a 1 mois·via RSSA theoretical separation between quantum computers & LLMsresearch.ibm.comIBM Research·il y a 1 mois·research.ibm.comil y a 1 moisA theoretical separation between quantum computers & LLMsRecent research further demonstrates the theoretical abilities of quantum computing
IBM ResearchLabo·en·il y a 2 mois·via RSSHow llm-d makes the most of the hardware you already haveresearch.ibm.comIBM Research·il y a 2 mois·research.ibm.comil y a 2 moisHow llm-d makes the most of the hardware you already haveIBM Research and Red Hat deployed a 753B open model on H100 GPUs, serving thousands of concurrent coding agents at 5-10x lower cost than commercial APIs.
