English

SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications

Computation and Language 2026-03-10 v3 Artificial Intelligence

Abstract

We present SwiftEmbed, a production-oriented serving system for static token embeddings that achieves 1.12\,ms p50 latency for single-text requests while maintaining a 60.6 MTEB average score across 8 representative tasks. Built around the open-source Potion-base-8M distilled model from MinishLab and implemented in Rust, the system delivers 50,000 requests per second through static embedding lookup, mean pooling, and zero-copy IEEE754 binary serialization. Evaluation demonstrates exceptional duplicate detection performance (90.1% AP) and strong semantic similarity (76.1% Spearman correlation). Performance relative to Sentence-BERT is task-dependent: robust for deduplication and similarity workloads (89--100%), substantially lower for classification and complex retrieval tasks (75%). Domain-specific performance ranges from 75% to 131% of a GloVe-840B baseline. The system targets real-time embedding applications where sub-5\,ms latency is operationally critical and where full transformer inference is not feasible.

Keywords

Cite

@article{arxiv.2510.24793,
  title  = {SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications},
  author = {Edouard Lansiaux and Antoine Simonet and Eric Wiel},
  journal= {arXiv preprint arXiv:2510.24793},
  year   = {2026}
}