mlsanityData to 14 Oct 2026

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

arXiv 2510.24793 ↗First posted 27 Oct 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

17 of 26 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  6. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  7. 2017Billion-scale similarity search with GPUscited by 2,497
  8. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  9. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  10. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  11. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,167
  12. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
5 more
  1. 2019Q-BERT: Hessian Based Ultra Low Precision Quantization of BERTcited by 359
  2. 2019Q8BERT: Quantized 8Bit BERTcited by 300
  3. 2023A Survey on Model Compression for Large Language Modelscited by 269
  4. 2023Transformer models: an introduction and catalogcited by 21
  5. 2021Obtaining Better Static Word Embeddings Using Contextual Embedding Modelscited by 18

Built on by

Not cited yet.