WebAssembly on the backend. Java on GPUs. Distributed AI inference at scale.
How are these technologies reshaping backend computing?
In this InfoQ podcast, Edoardo Vacchi explores TornadoVM, llm-d, and vLLM on Kubernetes, including how smarter cache management and request routing maximize expensive GPU utilization.
🎧 Listen now: https://www.infoq.com/podcasts/distributed-llm-inference-kubernetes/
Comments (0)
Sign in to comment