Login
A new plugin can enable fast runtime monitoring and control
21 October 2026 at 12:00
IBM's vLLM-Hook MIA lets developers inspect and edit the AI generation process with hardly any delay.
Normal view
llm-d 1.0 hardens open-source AI inference for production
20 October 2026 at 12:00
The distributed inference framework makes serving large models on your own infrastructure reliable and affordable for the agentic era.
How distributed inference keeps large AI models moving
12 October 2026 at 04:00
Distributed inference serving is an air traffic control tower for AI traffic, and agentic workflows make it more necessary than ever.
How llm-d makes the most of the hardware you already have
8 September 2026 at 12:00
IBM 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.
