Gpu Acceleration With Optional Fastembed Gpu Package

via “gpu acceleration via optional fastembed-gpu package”

Fast local embedding generation — ONNX Runtime, no GPU needed, text and image models.

Unique: Maintains API compatibility between CPU and GPU implementations, allowing users to switch backends without code changes; optional fastembed-gpu package keeps CPU version lightweight while enabling GPU acceleration for users with hardware

vs others: Simpler GPU setup than manual CUDA + ONNX configuration; maintains single codebase for both CPU and GPU paths; enables gradual migration from CPU to GPU without refactoring