AMD adds day 0 support for Qwen 3.5 large language models on Instinct GPUs

AMD is rolling out day 0 support for Alibaba's Qwen 3.5 large language models on its Instinct MI300X, MI325X, and MI355X accelerators, targeting developers building advanced Artificial Intelligence agents and enterprise platforms.

AMD is introducing day 0 support for Alibaba’s Qwen 3.5 large language models on its Instinct MI300X, MI325X, and MI355X GPU accelerators, delivered in close collaboration with the Alibaba Qwen team. The enablement relies on the optimized ROCm software stack together with the SGLang and vLLM inference serving frameworks, so developers can immediately deploy the new models on AMD hardware. The integration is positioned for production use rather than experimentation, focusing on performance and deployment readiness.

The strategic focus is on empowering next generation Artificial Intelligence agents and enterprise platforms by removing previous trade offs between parameter depth and reasoning speed. According to AMD, the Qwen 3.5 family on Instinct GPUs is tuned for workloads where both complex reasoning and fast responses are required, such as orchestration layers, intelligent assistants, and multi agent systems. The combination of Qwen 3.5 and Instinct accelerators is presented as a way to run demanding language and reasoning tasks at scale.

Qwen 3.5 models running on AMD Instinct hardware are highlighted for their ability to deploy massive 256K context windows and complex multimodal workflows with high efficiency. The large context window is aimed at use cases that need long term memory, extensive documents, or multi step interactions, while multimodal capabilities target scenarios that mix text with other data types. With ROCm, SGLang, and vLLM in place from day 0, Artificial Intelligence developers, system architects, and DevOps teams can start building and serving these workloads immediately on MI300X, MI325X, and MI355X based infrastructure.

55

Impact Score

Engineering news highlights from mit school of engineering

Mit school of engineering showcases recent research breakthroughs, educational initiatives, and community achievements across multiple departments and institutes. The updates span topics from artificial intelligence and biotechnology to climate science, robotics, and student innovation.

Samsung revamps HBM4E power delivery to cut defects and improve reliability

Samsung is redesigning the power delivery network in its HBM4E memory to manage rising current density and heat as power bumps increase, reporting sharp reductions in defects and voltage drop. The changes aim to support higher speeds and more reliable performance for next generation Artificial Intelligence accelerators.

UK artificial intelligence skills drive needs deeper, role-specific training

The UK government’s £27m artificial intelligence skills initiative aims to train 10 million people through free online courses, but businesses are warned that outdated, generic content will not close critical capability gaps. Organisations are urged to embed tailored, continuous artificial intelligence learning strategies that link directly to operational value and return on investment.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.