AMD has introduced a new plugin called vLLM-ATOM, which supercharges AI LLMs while supporting its Instinct MI350 and MI400 GPUs. AMD Offers Big Boost To AI LLMs With Its vLLM-ATOM Plugin That Works Seamlessly With vLLM & Accelerates AI Inference Performance The vLLM-ATOM is a purpose-built plugin that aims to improve inference performance across various AI LLMs. It is designed around AMD's high-performance Instinct GPU accelerators, such as the MI350 and MI400 series, running both as a standalone inference server or through seamless integration as a plugin backend. This allows users to take full advantage of AMD's native model and […]

Read full article at https://wccftech.com/amd-vllm-atom-plugin-supercharges-deepseek-r1-kimi-k2-gpt-oss-120b-ai-llm-inference-on-instinct-mi350-mi400/

AMD's immense success for its CPUs and GPUs in the AI segments will be a key driver for the company in the current year & the years ahead. AMD Is Expected To Ship Nearly 1.9 Million AI GPUs By 2027, While It's Share In China Will Be Larger Than NVIDIA's Intel, gaining momentum this quarter, thanks to Agentic AI's reliance on CPUs, has given us a teaser of what to expect from AMD's upcoming earnings. As per UBS, AMD isn't as constrained as Intel in the CPU segment and is anticipated to grow its Server CPU revenue by 80% this […]

Read full article at https://wccftech.com/amd-server-cpu-revenue-to-surge-80-percent-2026-estimated-1-9m-ai-gpus-shipping-by-2027/

AMD has rolled out official support for Google's Gemma 4 across its full range of GPUs & CPUs, offering support for the compact AI model. AMD Radeon GPUs & Ryzen AI CPUs Fully Support Google's Gemma 4 AI Model Google rolled out its latest family of open-weights AI models, called Gemma 4, which span a range of sizes, from 2B to 31B. With this announcement, AMD is rolling out support across its entire Radeon GPU, and Ryzen AI CPU family. Press Release: AMD is proud to provide Day Zero support for the full set of Gemma 4 models across our portfolio of AI-enabled […]

Read full article at https://wccftech.com/amd-rolls-out-gemma-4-model-support-across-full-range-of-gpus-cpus/