#220·nano-vllm

[Feature Request] Support weightless RMSNorm (for FlashNorm weight folding trick)

Author: NilsGrafCreated Apr 29, 2026Updated May 6, 2026

Please add support for RMSNorm without normalization weights.

This is to support FlashNorm — a mathematically equivalent variant of RMSNorm that folds norm weights into the subsequent linear layer. See explainer video.

We have applied this weight folding trick to a few LLMs (Llama, Qwen, SMolLM) here: https://huggingface.co/models?other=weightless-rmsnorm

Image

Motivation

FlashNorm's removal of norm weights reduces inference overhead at zero accuracy cost, and we'd like to share these optimized models with the broader community.

Possible Implementation

Remove norm weights from your RMSNorm implementation. E.g., just skip norm weight multiplication if there are no norm weights provided.

Source: GeeeekExplorer/nano-vllm