Tag
David Hodge built SatRadar, a browser-based tool that displays over 10,000 active satellites in real-time at up to 120 FPS by running the SGP4 orbital propagator entirely on the GPU via WebGL2 shaders.
Japanese apparel giant ZOZO has open-sourced its internal top physics engine ppf-contact-solver, which specializes in solving contact and collision problems for fabrics, ropes, and soft bodies, with zero penetration. It supports Blender plugin and GPU acceleration, and can be used free of charge for virtual fashion, digital clothing, movie VFX, game physics, and more.
The article highlights the new WebGPU backend in llama.cpp/ggml, enabling GPU-accelerated local AI model inference in browsers, developed by Reese Levine and team at USCS over the past year and a half.
This paper presents a GPU-accelerated deep learning framework using ConvLSTM models to predict next-day urban thermal conditions and generate heat risk maps, achieving strong performance (R²=0.8877) on Sarajevo data.
The article announces support for DFlash and PFlash speculative decoding in llama.cpp for AMD Strix Halo iGPUs, demonstrating significant speedups in inference performance using ROCm.
User @binsquares reports that GPU acceleration on smolvm achieves nearly 90% of host performance when running llama.cpp via the Vulkan backend.
vLLM v0.20.1 is a minor version update for the popular open-source LLM inference and serving library, maintaining its focus on high-throughput and efficient memory management.
easyaligner is an open-source forced alignment library with GPU acceleration and flexible text normalization that works with all wav2vec2 models on Hugging Face Hub. It addresses practical workflows like handling partial transcripts, irrelevant speech segments, and long audio without chunking while preserving original text formatting.
Adobe announced a new Color Mode in Premiere Pro, optimized with NVIDIA GPU acceleration for 32-bit color grading, showcased at NAB 2026.
OpenAI open-sources mujoco-py, a high-performance Python library for robotic simulation using the MuJoCo engine, featuring ~40x speedup with headless GPU rendering and VR interaction support.
transcribe.cpp is a C/C++ speech-to-text inference library that supports 16 model families and 60+ variants via GGUF on the ggml runtime, offering GPU backends (Metal, Vulkan, CUDA) and CPU inference.