Computer Architecture

Browse all books in this category

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

<h2 class="text-2xl font-bold mb-4">Summary</h2> The paper introduces Switch Transformers, a novel architecture designed to scale language models to trillions of parameters. It leverages a mixture-of...

RWKV: Reinventing RNNs for the Transformer Era

RWKV: Reinventing RNNs for the Transformer Era

<h2 class="text-2xl font-bold mb-4">Summary</h2> This paper introduces RWKV, a novel architecture that seeks to combine the strengths of both Recurrent Neural Networks (RNNs) and Transformers. RWKV a...

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

<h2 class="text-2xl font-bold mb-4">Summary</h2> DeepSeek-V2 presents a Mixture-of-Experts (MoE) language model designed for strong performance, economic efficiency, and operational efficiency. The p...