41554 blogs · 4,756,248 posts Claim your blog

Record · corpus.blog/posts/01a087c8-fa54-708d-80b7-8207374c1a69

Gated Delta Net Attention: A Deep Dive into the Linear Attention Mechanism Powering Qwen3.5

pramodith.github.io · published 25 March 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at pramodith.github.io Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 12
Words captured: 5,358

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://allenai.org/blog/olmohybrid

allenai.org

https://sebastianraschka.com/llm-architecture-gallery/

sebastianraschka.com

https://huggingface.co/spaces/HuggingFaceTB/smol-training-playbook

huggingface.co

https://arxiv.org/pdf/2412.06464

arxiv.org

https://github.com/pramodith/llm_exploration/blob/main/gated_delta_net/householder.ipynb

github.com

https://pramodith.github.io/assets/img/favicons/2026-03-25-gated-delta-net/householder_beta_2.png

pramodith.github.io

https://pramodith.github.io/assets/img/favicons/2026-03-25-gated-delta-net/householder_beta_1.png

pramodith.github.io

https://arxiv.org/pdf/2507.06457

arxiv.org

https://github.com/NVlabs/GatedDeltaNet/tree/main

github.com

https://github.com/NVlabs/GatedDeltaNet/blob/main/lit_gpt/gated_delta_net.py

github.com

https://github.com/rasbt/LLMs-from-scratch/blob/main/ch04/08_deltanet/README.md

github.com

https://github.com/fla-org/flash-linear-attention/tree/main/fla/ops/gated_delta_rule

github.com