A developer's optimization campaign on an RTX 3080 Ti cut a GPT-2-small-class transformer's forward pass from 78.2ms to 1.60ms, a 49× speedup, beating torch.compile's 1.72ms and reaching 136,000 token…
A developer has published a practical guide for setting up a local AI troubleshooting and support environment on macOS and Windows using Open WebUI, Ollama, and Hugging Face. The recommended architect…
NVIDIA has brought its RTX Neural Texture Compression (NTC) technology to Windows-on-Arm, ahead of the general release of its RTX Spark PC platform. NTC, first demonstrated at GTC 2026 in May, can red…
Hazy Research, the team behind ThunderKittens and Megakernels, argues that CUDA domain-specific languages (DSLs) are heading toward retirement as AI agents take over the cognitive offloading role that…
AlphaPebble Labs engineers detailed a field guide for training AI models on RunPod's rented GPU infrastructure, highlighting edge cases such as the SSH gateway acting as a console rather than an exec …
An M.Tech thesis at IIT Bhilai implemented GPU acceleration for the MSCRED multivariate time-series anomaly detection model, achieving a 12.68× encoder speed-up by using CUDA and an im2col plus GEMM a…
AMD reported record second-quarter revenue of $11.5 billion, up 50% year over year, with data center revenue reaching $6.7 billion, up 107%, as CEO Lisa Su said open-source contributions to its ROCm s…
AMD executives say the chip company's open-source strategy gives it an edge over Nvidia in the AI chip race, with CEO Lisa Su noting that open-source contributions to its ROCm software have increased …
Perplexity is hiring a Member of Technical Staff (Software Engineer, GPU Cluster Infrastructure) in San Francisco with a salary range of $250k–485k/yr, to build a self-serve compute platform for its G…
A developer has open-sourced a Decay-Gated O(N) Causal Linear Attention architecture with fused Triton/CUDA kernels, aiming to bypass quadratic multi-head attention bottlenecks. The project includes a…
AI coding agents are eroding Nvidia's CUDA software moat by lowering the expertise barrier for GPU kernel development, according to a tech analysis. Tools like Anthropic's Claude Code can generate per…
The US lead over China in AI has essentially disappeared, according to an analysis of model releases and deployment trends. Chinese models like DeepSeek's R1 and V3 and Qwen now match or beat US open-…
Nvidia's CUDA software moat is being challenged as AI coding agents recreate similar software in hours, according to Jeremy Nixon, founder of AI software startup Infinity, whose team built CUDA-like s…
The cuda-oxide project introduces proof-carrying views that eliminate bounds-check overhead in CUDA kernels written in Rust, boosting GEMM performance from 2,942 to 7,159 GFLOPS (2.43x) with only ~0.1…
Quartz, a from-scratch Rust inference engine developed by Saient, has been open-sourced, enabling on-device video generation with Wan2.1 T2V (1.3B parameters) on a Samsung Galaxy S24's Vulkan GPU, alo…
Hygon Information Technology Co., Ltd. has unveiled a 512-thread x86 CPU and an AI GPU, positioning itself as a potential rival to Intel Corporation's Xeon processors and Nvidia Corporation's datacent…
Qualcomm closed its all-stock acquisition of Modular Inc. on July 29, 2026, issuing up to 19.2 million shares valued at approximately $3.9 billion, gaining Modular's CUDA-independent AI software stack…
PyTorch's multiprocessing module provides a CUDA Inter-Process Communication (IPC) API that enables sharing model weights across multiple processes for inference, avoiding duplication in GPU VRAM. The…
NVIDIA has open-sourced its Linux GPU kernel modules, including nvidia.ko, nvidia-drm.ko, nvidia-uvm.ko, and nvidia-modeset.ko, while keeping user-space components like CUDA and GSP firmware proprieta…
Researchers at UC Berkeley Sky Lab extended the K-Search evolutionary kernel optimization framework with a CUDA-to-MLX translation layer, enabling automatic transfer of GPU kernel expertise from NVIDI…