Search Results for "free gpu"

Open-LLM-VTuber is an open source platform designed to create AI-powered VTuber characters that can interact with users through voice and animated avatars. It enables hands-free conversations with large language models by combining speech recognition, language processing, and text-to-speech synthesis into a single system. Users can speak directly to the AI character, and the system can respond with a generated voice while animating a Live2D avatar to simulate a talking virtual personality....

The shimmy project is a lightweight local inference server designed to run large language models with minimal overhead. Written primarily in Rust, the tool provides a small standalone binary that exposes an API compatible with the OpenAI interface, allowing existing applications to interact with local models without significant code changes. This compatibility enables developers to replace remote AI services with locally hosted models while keeping their existing software architecture...

What happens when is a large collaborative documentation-style project that aims to answer in exhaustive detail the canonical interview/thought experiment question, “What happens when you type google into your browser and press Enter?” Rather than giving a high-level overview, the repository tries to break down every step in the process, from low-level events (keyboard press, OS events, keyboard interrupts), through OS-level handling (keyboard scan codes, key events), parsing, DNS lookup,...

FastFlow is a C/C++ programming framework supporting the development of pattern-based parallel programs on multi/many-core, GPUs and distributed platforms. FastFlow run-time is built upon non-blocking threads and lock-free queues. Thanks to its very efficient CAS-free communication/synchronization support (e.g. few clock cycles core-to-core latency), FastFlow effectively supports the exploitation of fine grain parallelism, e.g. parallel codes managing very high frequency streams on...

DualSPHysics is based on the Smoothed Particle Hydrodynamics method and can be downloaded from the official website (www.dual.sphysics.org). The code is developed to study free-surface flow phenomena where Eulerian methods can be difficult to apply, such as waves or impact of dam-breaks on off-shore structures. DualSPHysics is a set of C++, CUDA and Java codes based on the SPHysics FORTRAN project (www.sphysics.org) that are designed to deal with real-life engineering problems and are...

...Because most work happens on the GPU, it scales well as the number of points grows and remains interactive for animations, live telemetry, or dynamic overlays. The library focuses on visual quality, producing anti-aliased, blur-free gradients that look good at various zoom levels and resolutions. It fits well into data-viz stacks where you need a responsive heat layer on top of maps, charts, or custom canvases, and it is compact enough to embed in dashboards and demos without heavy dependencies.

...To access and download the code, please review the code section. (The code section is currently close until our article gets published) Commiting publicly to the project is currently closed but feel free to email us. The source code is dependant on CUDA 5.0 Samples now available as part of the CUDA Toolkit. "This software contains source code provided by NVIDIA Corporation."

A Lightweighted Toolkit For Volume Rendering Project Started by Fei Yang Provide both CPU based and GPU (CUDA) based volume rendering. See http://www.fei-yang.org/?page_id=12 for complete descriptions and package downloads VolTK is a free C++ Toolkit that implements a tri-layer volume rendering framework, which is designed to meet the requirements of both algorithm research and application assemblage. Features * Tri-layer volume rendering * CPU implementation: multi-threading supported * GPU implementation: CUDA based implementation * CPU-GPU correspondance * Both low level interfaces and high level interfaces are provided * Replace the components easily with your own design * Various rendering modes: MIP/Isosurface/Full volume rendering * Endoscopy interaction mode implemented * Pre-integration supported * Cross platform (windows and RHEL tested)

GPT-OSS-120B is a powerful open-weight language model by OpenAI, optimized for high-level reasoning, tool use, and agentic tasks. With 117B total parameters and 5.1B active parameters, it’s designed to fit on a single H100 GPU using native MXFP4 quantization. The model supports fine-tuning, chain-of-thought reasoning, and structured outputs, making it ideal for complex workflows. It operates in OpenAI’s Harmony response format and can be deployed via Transformers, vLLM, Ollama, LM Studio,...