IBM Research

What does it take to support new AI hardware within PyTorch? In our latest blog, contributors from @IBM share how they extended PyTorch Inductor for the IBM Spyre Accelerator, leveraging PyTorch's compiler to address challenges in data movement, memory management, and work distribution while optimizing for Spyre's unique architecture. Read on for a look at how PyTorch's extensibility helps developers bring support for new hardware to the framework: bit.ly/4dCdqxW

@IBMResearch and PyTorch continue to push the boundaries of AI infrastructure and open source innovation. Join us at #PyTorchCon 2026 for a keynote from @PriyaNagpurkar, VP of AI-native Systems Research at IBM, technical sessions covering vLLM and PyTorch performance, and interactive demos featuring the llm-d project and the IBM Spyre Accelerator. Register: bit.ly/4sh3DSw View IBM's conference agenda, accepted publications, and related press: ibm.biz/pytorch2026

Get more out of your AI infrastructure. Carlos Costa, Distinguished Engineer at @IBMResearch and co-founder of the @_llm_d_ project will share some exciting news about llm-d: how the project changed the way the open source AI community scales inference at PyTorch Conference North America. A little over a year after the project was founded, llm-d is reaching a new level of maturity, delivering state-of-the-art performance for generative serving, while also enabling the capabilities needed for day two operations, including multi-tenant quality of service, zero downtime operations, and all of that without sacrificing performance in production. Join us in San Jose, October 20-21: hubs.la/Q04v4SL60

PyTorch Conference is where the open source Al community gathers to talk about what we are all building together. Priya Nagpurkar, VP of AI Native Systems at @IBMResearch will give a keynote at #PyTorchCon North America on @IBM & @RedHat's contributions to the PyTorch ecosystem, including exciting developments on infrastructure for out-of-tree accelerators, enablement of IBM's Spyre Accelerator, and work with Ilm-d for distributed inference. Come to the talk, meet the community, and hear what's next in open source Al. Join us in San Jose, October 20-21: hubs.la/Q04v4SL60