| The 2025.0 release of Intel® oneAPI & AI Tools is now available, coinciding with the 5-year anniversary of the oneAPI initiative, one of the most eminent programming standards for data-centric heterogeneous computing. Download them today and join the global ecosystem of 6.8 million developers who use them to build, optimize, and deploy high-performance software that can run on any vendor architecture. 3 Key Benefits - More Performance on Intel Platforms – Achieve up to 3x higher GenAI performance on Intel® Xeon® 6 processors (P-cores) with oneDNN, Intel-optimized AI frameworks, and Intel® AMX1; achieve up to 2.5x better HPCG performance with MRDIMM2 and oneMKL; develop high-performance AI on PCs powered by Intel® Core™ Ultra processors (Series 2); and improve security and encryption with Intel® Cryptography Primitives Library.
- More Access to Industry-Standard Tools – Get more from your existing development workflows with built-in optimizations for AI frameworks and libraries, including native support for PyTorch 2.5 on Intel CPUs and GPUs; achieve optimal performance across CPU, GPU, and AI accelerators from the latest LLMs—Llama 3.2, Qwen2, Phi-3; and streamline your software setup with our toolkit selector to install only what you need.
- More Hardware Choices – Enjoy increased multi-vendor, multiarchitecture support, including faster CUDA-to-SYCL migration of over 100 APIs used by popular AI, HPC, and rendering apps; achieve near-native performance on CPU and GPU for numeric compute with Intel’s Python distribution; get 4x speedup of GPU kernels for algorithms with oneDPL3; and gain future system flexibility through cross-hardware AI-acceleration libraries, including Triton, JAX, and OpenXLA.
Get the details & links | Learn about oneAPI’s 5th Anniversary  1 See [9A2] at intel.com/processorclaims: Intel® Xeon® 6. Results may vary.
2 See [9H10] at intel.com/processorclaims: Intel® Xeon® 6. Results may vary.
3. See oneDPL product page | 
