IBM Spyre joins PyTorch compiler and vLLM, Red Hat builds CI/CD
Hardware vendors gaining first-class PyTorch and vLLM support means open-source inference stacks are extending beyond NVIDIA GPUs to dedicated AI accelerators. Teams building multi-backend deployments should watch llm-d and the out-of-tree accelerator CI/CD work, which lower the cost of adding new hardware backends. Spyre's path contrasts with closed proprietary stacks like NVIDIA's CUDA ecosystem.
At PyTorchCon 2026, IBM's Priya Nagpurkar presented “From Silicon to Models at Scale” on 2 Sep 2026. She described work integrating IBM Spyre hardware into the PyTorch compiler and vLLM. IBM uses AI tooling to enable thousands of models, and previewed next-generation Spyre hardware. Red Hat contributes PyTorch CI/CD infrastructure for out-of-tree accelerators and works with the llm-d community on distributed inference.
Priya Nagpurkar (@IBM) shares how IBM and @RedHat contribute across the PyTorch ecosystem in “From Silicon to Models at Scale” at #PyTorchCon 2026.
Priya highlights work bringing IBM Spyre to the PyTorch compiler and vLLM, how AI tools help scale model enablement to thousands of models, and a look ahead at next-generation Spyre hardware.
She discusses Red Hat’s contributions to PyTorch and CI/CD infrastructure for out-of-tree accelerators, helping hardware backends keep pace with the community, alongside work with the llm-d community toward efficient distributed inference at scale.
- marktechpost10-21 04:33原文
