LongCat 2.0 is Meituan's 1.6T-parameter MoE model with a native 1M-token context, trained entirely on domestic AI ASIC ...
Jeff Bezos has put money behind one of the most contrarian bets in artificial intelligence. Flourish, a neuroscience-focused AI startup, has raised $500 million at a $2.5 billion valuation from a ...
A lightweight and efficient library for operations on block-sparse matrices in PyTorch using Triton.
As with this library sparse matrices are represented using a tuple of (matrix, sparsity_layout, sparsity_block_size), any element-wise operations can be applied in regular torch-like fashion. These ...
Large language models (LLMs) have become crucial tools in the pursuit of artificial general intelligence (AGI). However, as the user base expands and the frequency of usage increases, deploying these ...
Abstract: Sparse General Matrix-Matrix Multiplication (SpGEMM) is a core operation in high-performance computing applications such as algebraic multigrid solvers, machine learning, and graph ...
DeepSeek unveils a new AI model focused on cost efficiency. The main innovation is a reduction in compute to run attention. The innovation is not revolutionary; it's evolutionary. Last week, DeepSeek ...
Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in ...
An energy-efficient chip called NeuRRAM fixes an old design flaw to run large-scale AI algorithms on smaller devices, reaching the same accuracy as wasteful digital computers. Artificial intelligence ...
This work proposed MaxK-GNN, an acceleration framework that integrates the maxk nonlinearity function into the GNN workflow. The innovation encompasses a coalescing enhanced forward computation ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results