KubeSwift, a Kubernetes-native VM orchestration platform built on Cloud Hypervisor, has been released with support for Linux and Windows guests, GPU passthrough, live migration, and 13 custom resource…
PyTorch 2.13 has been released with performance improvements including FlexAttention on Apple Silicon with up to 12x speedups, a CuTeDSL backend for Inductor, and fused nn.LinearCrossEntropyLoss reduc…
A developer added opt-in GPU backends (Metal and CUDA) to a pure-C TTS inference engine for Qwen3-TTS, achieving faster-than-real-time performance on Apple Silicon and NVIDIA GPUs. The key optimizatio…
A developer released TexasSolver GPU, a free, GPU-accelerated Texas Hold'em GTO solver built with C++ and CUDA, claiming faster solving speeds than previous tools. The software offers features like ba…
Nvidia became the first company to reach a $5 trillion market capitalization on October 29, 2025, driven by its early bet on parallel computing through CUDA in 2006. The company's chips, initially use…
AMD has brought PyTorch Monarch to its Instinct GPUs with ROCm, enabling single-controller distributed training for large language models. The port addresses reliability challenges at scale by providi…
PyTorch's test infrastructure dynamically generates test names across devices and dtypes, causing CI failures to show names like TestLinalgCUDA.test_matmul_cuda_float32 that differ from source templat…
Transcribe.cpp, a C/C++ speech-to-text inference library, has been released supporting 16 model families and 60+ variants via GGUF models on the ggml runtime. It offers Metal, Vulkan, and CUDA backend…
Andrzej Janik released ZLUDA v6 on June 29, adding 32-bit PhysX support and AI workload improvements, but announced commercial funding has ended for the third time, returning the project to a weekend …
Nvidia dominates AI training hardware, but the inference market is wide open as companies like Cerebras, Groq, d-Matrix, Etched, and Taalas challenge Nvidia's GPU-based approach by designing chips opt…
NVIDIA used Nsight Systems and Nsight Compute to optimize its NuRec neural reconstruction pipeline, reducing reconstruction times from hours toward a goal of real-time performance for autonomous vehic…
Jaiveer Singh, a robotics software engineer at NVIDIA, leads the team behind Isaac ROS, an open-source framework that accelerates development of autonomous robots using CUDA-accelerated libraries and …
The KV cache accelerates LLM inference on GPUs by storing prior token key/value projections instead of recomputing them, reducing per-step attention cost from quadratic to linear. Decode is memory-ban…
Handy Computer released transcribe.cpp, an open-source ggml-based transcription library supporting over 60 ASR models with GPU acceleration via Vulkan, Metal, CUDA, and TinyBLAS. The library, created …
ZLUDA version 6 has been released, enabling unmodified CUDA applications to run on non-Nvidia GPUs. The update adds support for PhysX and Blender workloads, improves Windows compatibility, and allows …
AMD stock surged over 114% year-to-date in 2026, outperforming Nvidia's modest 12-18% gain, as investors bet on AMD's competitive AI chips like the MI350X and its strategy to win hyperscaler contracts…
NVIDIA's CUDA kernel launch involves a multi-stage compilation pipeline from C++ to PTX virtual ISA to SASS machine code, followed by runtime coordination via ioctl system calls and doorbell register …
NVIDIA's CUDA compiler pipeline transforms a simple vector addition kernel from PTX virtual assembly to SASS machine code through multiple compilation stages, including LLVM-based cicc and ptxas, befo…
Samuel Yuan, a developer from MIT, released wavecat, a fully local personal AI agent that continuously watches a user's screen to understand their activity and goals, with all processing and data stor…
Developer Vincenzo released NanoEuler, a from-scratch GPT-2-scale language model training stack written in C and CUDA without PyTorch or autograd, on June 28, 2026. The 116-million-parameter project i…