Show HN: I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT)

Category: infrastructure

Tags: embedding, rust, tensorrt, gpu, nlp

Score: 8.0/10 (Innovation: 8, Technical: 9, Documentation: 7, Utility: 8)

IgniteMS is a high-performance batch text embedding engine written in Rust that leverages native TensorRT for GPU inference, achieving up to 3.6x speedup over Hugging Face TEI. Its innovative design combines bucketed batching, lock-free multi-GPU work stealing, and a full Rust pipeline to eliminate Python overhead, making it exceptionally efficient for large-scale corpus embedding tasks.

Target audience: data engineers, ml engineers, backend devs

Repository: https://github.com/Artain-AI/ignite-ms · Rust · Apache-2.0

View on Hacker News