github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15913] [Feature Request] Support weightless RMSNorm (for FlashNorm weight folding trick) #72195

New Issue
Open
opened 2026-05-05 03:37:15 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 03:37:15 -05:00
Owner
Copy Link

Originally created by @NilsGraf on GitHub (May 1, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15913

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.

Originally created by @NilsGraf on GitHub (May 1, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15913 Please add support for RMSNorm without normalization weights. This is to support [FlashNorm](https://arxiv.org/abs/2407.09577) — a mathematically equivalent variant of RMSNorm that folds norm weights into the subsequent linear layer. [See explainer video](https://www.youtube.com/watch?v=GEuJv34_XgU). We have applied this weight folding trick to a few LLMs (Llama, Qwen, SMolLM) here: https://huggingface.co/models?other=weightless-rmsnorm <img width="332" height="183" alt="Image" src="https://github.com/user-attachments/assets/d97b50ba-1092-4d44-ad70-ff2bca448b1d" /> ### 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.
GiteaMirror added the feature request label 2026-05-05 03:37:15 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#72195
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?