FirsthandTech
arXiv: cs.AI preprintsInternational20 November 2026

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

This is an official announcement record

Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.

arXiv:2606.26587v2 Announce Type: replace-cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent outliers that dominate block scales in FP4 quantization, and directly applying N:M sparsity masks discards moderate values, coupling sparsification loss with quantization error. We introduce SharQ, a training-free inference method that bridges activation sparsity and FP4 quantization through an online sparse--dense decompo
Source: arXiv: cs.AI preprints

More from arXiv: cs.AI preprints

This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.