Artain-AI/ignite-ms

Fast self-hosted embedding engine for search, RAG, and reindexing workloads on NVIDIA GPUs. Built in Rust + TensorRT for teams that care about scale, cost, and control.

语言：Rust · GitHub 星标：9 · Fork：0

话题：batch-inference · batch-processing · cuda · embeddings · gpu · high-performance · huggingface · machine-learning

在 GitHub 上查看原仓库