Explore the potential integration of GPU offloading models with WebAssembly (WASM) in this conference talk by Intel experts. Delve into the growing importance of parallelization in AI workloads and the challenges of implementing GPU support in WASM environments. Learn about the current limitations of WASM in handling multithreaded, shared memory, vectorized, and device offloaded workloads. Discover the ongoing efforts to integrate CPU-based OpenMP with WASM and the investigation into GPU offloading models such as OpenMP, CUDA, and SYCL. Understand the security implications and potential benefits of incorporating GPU offloading capabilities into WASM, paving the way for more secure, portable, and cloud-compatible AI applications.