AI & machine learning2020 · shared on Hacker News
Faster Autoregressive Transformers with Linear Attention
Explore Faster Autoregressive Transformers with Linear Attention, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ygnyeki ·
My Python code is a neural network
331 points67 comments
Ybratao ·
Mamba-2 – State Space Duality
151 points33 comments
Ytaiboku256 ·
Ask HN: Is anybody building an alternative transformer?
148 points93 comments
Yfzliu ·
LM2: Large Memory Models
110 points30 comments
Ydatashrimp ·
The Reformer – Pushing the limits of language modeling
62 points13 comments
YPaulHoule ·
Architectural Effects on Maximum Dependency Lengths of Recurrent Neural Networks
23 points3 comments
Ycocacola1 ·
There Is No A.I
17 points9 comments
Ymatt_d ·
FlashAttention-T: Towards Tensorized Attention
12 points0 comments
Yfheinsen ·
Attention at Constant Cost per Token via Symmetry-Aware Taylor Approximation
8 points0 comments
Ygolol ·
What a transformer can NOT do
7 points1 comments
Yfofoz ·
Faster Autoregressive Transformers with Linear Attention
6 points0 comments
Ymaraoz ·
ChatRWKV, like ChatGPT but powered by the RWKV (RNN-based, open) language model
1 points0 comments