Blog

We’re excited to announce MAX 25.2, a major update that unlocks industry-leading performance on the largest language models–built from the ground up without CUDA.

We recently introduced MAX 25.1, a major leap forward in AI development. This release enhances agentic and LLM workflows, introduces MAX Builds as a central hub for GenAI models and application recipes, and debuts a new GPU programming interface. Developers can now take advantage of GPU-accelerated embeddings, OpenAI-compatible function calling, structured output generation, and high-performance LLM optimizations like paged attention and prefix caching for improved efficiency.

Answering the question of whether CUDA is “good” is much trickier than it sounds.

If we as an ecosystem hope to make progress, we need to understand how the CUDA software empire became so dominant.

PagedAttention & Prefix Caching Now Available in MAX Serve

Part 1 of an article that explores the future of hardware acceleration for AI beyond CUDA, framed in the context of the release of DeepSeek