#Nvidia

Under the Hood of a CUDA Kernel Launch

From triple-angle brackets to SASS assembly and doorbell registers, here is how NVIDIA orchestrates GPU execution.

Article · 1d ago0

Under the Hood of NeMo AutoModel: High-Performance MoE Fine-Tuning

NVIDIA's new library injects Expert Parallelism and DeepEP into Hugging Face's API, slashing memory use and training times.

Article · 6d ago0

The Architecture of Monopoly: Inside NVIDIA's Supercomputing Hegemony

NVIDIA now powers 81 percent of the world's fastest supercomputers, forcing a fundamental rewrite of high-performance software.

Article · 1w ago0

Inside NVK's Experimental DLSS: A Clever Hack for Open-Source Linux

By importing pre-compiled CUDA binaries, the open-source NVK Vulkan driver bypasses Nvidia's proprietary compiler barrier—with significant caveats.

Article · 1w ago2

AMD's $3,999 Ryzen AI Halo Challenges Nvidia's DGX Spark

A compact developer kit brings 128GB of unified memory and Windows support to local AI workstation workloads.

News · 2w ago0

Inside NVIDIA Cosmos 3: Mixture-of-Transformers for Physical AI

The open-source platform unifies autoregressive reasoning and diffusion-based generation into a single architecture for robotics and autonomous systems.

Release · 2w ago1