Skip to main content
Search

# Structured Pruning

1 related articles

Subscribe to updates
  1. arXiv

    LLaMA3-8B cut to 4.5B parameters: SlimFM moves LLM semantics into online CTR serving at about 16 ms

    Adding large-language-model semantics to click-through-rate prediction previously meant caching LLM outputs offline and serving only a small CTR model online. SlimFM prunes LLaMA3-8B to a 4.5B-parameter backbone with dependency-aware structured pruning, fine-tunes it with LoRA for field-level semantic embeddings, and injects those embeddings into a conventional CTR model's feature interactions. Across four datasets and six CTR backbones it retains over 99% of the uncompressed model's accuracy, with single-sample inference latency of 15.98–17.58 ms.

You’re all caught up