New GPUBreach attack enables system takeover via GPU rowhammer
(bleepingcomputer.com)
61.
62.
Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU
(news.ycombinator.com)
63.
BarraCUDA Open-source CUDA compiler targeting AMD GPUs
(news.ycombinator.com)
64.
Show HN: AutoShorts – Local, GPU-accelerated AI video pipeline for creators
(news.ycombinator.com)
65.
Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks
(news.ycombinator.com)
66.
67.
Gaussian Splatting 3 Ways
(news.ycombinator.com)
68.
TRELLIS.2: state-of-the-art large 3D generative model (4B)
(news.ycombinator.com)
69.
CUDA-l2: Surpassing cuBLAS performance for matrix multiplication through RL
(news.ycombinator.com)
70.
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication Through RL
(news.ycombinator.com)
71.
CUDA Ontology
(news.ycombinator.com)
72.
73.
VectorWare – from creators of `rust-GPU` and `rust-CUDA`
(news.ycombinator.com)
74.
Nvidia DGX Spark: great hardware, early days for the ecosystem
(news.ycombinator.com)
75.
The math behind tiled v/s naive matrix multiplication in CUDA
(news.ycombinator.com)
76.
A Gentle Introduction to CUDA PTX
(news.ycombinator.com)
77.
Nvmath-Python: Nvidia Math Libraries for the Python Ecosystem
(news.ycombinator.com)
78.
Show HN: I Parallelized RNN Training from O(T) to O(log T) Using CUDA
(news.ycombinator.com)
79.
80.
Accelerated Game of Life with CUDA / Triton
(news.ycombinator.com)
81.
Show HN: An ncurses CUDA-based fluid simulation
(news.ycombinator.com)
82.
Writing Speed-of-Light Flash Attention for 5090 in CUDA C++
(news.ycombinator.com)
83.
Show HN: CUDA Fractal Renderer
(news.ycombinator.com)
86.
Apple's MLX adding CUDA support
(news.ycombinator.com)
87.
Asynchronous Error Handling Is Hard
(news.ycombinator.com)
88.
CUDA Ray Tracing 2x Faster Than RTX: My CUDA Ray Tracing Journey
(news.ycombinator.com)
89.
Show HN: I built a tensor library from scratch in C++/CUDA
(news.ycombinator.com)
Today's top topics:
openai
anthropic
apple
ai safety
google
ios 27
dario amodei
iphone 18 pro
nvidia
microsoft