Search Results for "gpu 0" - Page 2
Sort By:
Showing 48 open source projects for "gpu 0"
View related business solutions-
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
StudioOllamaUI
StudioOllamaUI is a local, portable interface for Ollama
StudioOllamaUI: Portable .The easiest way to run local AI Do you want to use AI but don't know what Docker is? Does the terminal scare you? StudioOllamaUI is for you. Zero Installation: Works on a fresh Windows installation. No Python, no libraries, no drama. 100% Portable: Just like a portable browser. Unzip, run, and that's it. It doesn't clutter your registry or leave traces on your disk. AI for Everyone: No expensive GPU? No problem. Optimized to run smoothly on your CPU and RAM. Total Privacy: Everything stays on your machine. ... -
2
KoboldCpp
Run GGUF models easily with a UI or API. One File. Zero Install.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features. -
3
Xray_OS
Xray_OS is Angel's own normal Linux distro.
Xray_OS is an Arch Linux distribution dedicated to technical excellence over corporate agendas or intrusive guidelines. Delivered with Systemd-Liberated and the Bazaar-Disinfected store (Custom Bazaar Store without rare progress bars or irrelevant political content) free from age-verification code or telemetry. Optimized for both workstations and gaming, Xray_OS includes its own low-latency BORE scheduler kernel (Linux Vita Kernel), NVIDIA autodetection, some DaVinci Resolve fixes for... -
4
Tableau
A lightweight macOS photo widget that never crops your images.
...Built with an ultra-efficient SwiftUI engine, it consumes almost zero idle CPU. -
Earn up to 16% annual interest with Nexo.Generate interest, access liquidity without selling, and execute trades seamlessly. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
5
usb-guard
Turn any USB flash drive into a master key for your PC
USB Guard is an advanced workstation security solution for Windows that turns USB drives into physical authentication keys using native Windows Kernel APIs. - Zero-Trust Security: Validates unique hardware serial numbers through direct Kernel API calls, ensuring only authorized USB drives can unlock your PC. - Brute-Force Protection: Exponential delay penalties after failed unlock attempts prevent automated attacks. - High-Fidelity Lock Screen: Glassmorphism aesthetics with GPU-accelerated blur effects that blend seamlessly with your desktop wallpaper... -
6
Abscom
A C11 library of reusable data structures and platform utilities.
Abscom bundles low-level building blocks — dynamic arrays, growable strings, hash functions, an open-addressing hash map, timing helpers, and simple file I/O — under a single umbrella header. On top of that it ships a Python-inspired dynamic runtime that brings var values, lists, dictionaries, sets, JSON, random utilities, and a light object system to plain C, plus a scientific layer with matrices, statistics, general math (scalar utilities, number theory, geometry, complex numbers), CSV,... -
7
NKTg AI NKTg AI Logo Language Decoding System Measure semantic structure. Extract Core Content. Support better decisions. Overview NKTg AI is a deterministic Language Decoding System that measures the semantic structure of text to identify its Core Content. Unlike traditional AI summarization systems, NKTg AI does not generate new information or rewrite documents. Instead, it analyzes the internal semantic structure of a text and extracts the sentence that carries the highest...
-
8
higgsfield
Fault-tolerant, highly scalable GPU orchestration
Higgsfield is an open-source, fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters, such as Large Language Models (LLMs). -
9
SSD in PyTorch 1.0
High quality, fast, modular reference implementation of SSD in PyTorch
This repository implements SSD (Single Shot MultiBox Detector). The implementation is heavily influenced by the projects ssd.pytorch, pytorch-ssd and maskrcnn-benchmark. This repository aims to be the code base for research based on SSD. Multi-GPU training and inference: We use DistributedDataParallel, you can train or test with arbitrary GPU(s), the training schema will change accordingly. Add your own modules without pain. We abstract backbone, Detector, BoxHead, BoxPredictor, etc. You can... -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
10
Aviary
Ray Aviary - evaluate multiple LLMs easily
...Supporting Transformer models hosted on Hugging Face Hub or present on local disk. Aviary has native support for autoscaling and multi-node deployments thanks to Ray and Ray Serve. Aviary can scale to zero and create new model replicas (each composed of multiple GPU workers) in response to demand. Ray ensures that the orchestration and resource management is handled automatically. Aviary is able to support hundreds of replicas and clusters of hundreds of nodes, deployed either in the cloud or on-prem. -
11
NBMiner
GPU Miner for ETH, RVN, BEAM, CFX, ZIL, AE, ERGO
nbminer.com & NBMiner_github are the only 2 officially maintained site for publishing information and new releases of NBMiner. Be aware when you download NBMiner binaries from other sources. For GPUs with Hynix GDDR6 memory, LHR mode is not recommended for the poor performance. Improve performance on Grin29 & AE. Add support for mining SERO, algo progpow_sero. Change devfee in percentage, [0-5]. Set to ‘0’ to turn off devfee with lower hash rate. Otherwise, devfee = max(set_value,... -
12
bert4keras
Keras implement of transformers for humans
...The original intention of this project is for the convenience of modification and customization, so it may be updated frequently. Load the pre-trained weights of bert/roberta/albert for fine-tune. Implement the attention mask required by the language model and seq2seq. Pre-training code from zero (supports TPU, multi-GPU, please see pertaining). Compatible with keras, tf.keras. -
13
What happens when
What happens when you type google into your browser and press enter?
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,... -
14
Intel compute-runtime
Intel® Graphics Compute Runtime
The Intel(R) Graphics Compute Runtime for oneAPI Level Zero and OpenCL(TM) Driver is an open source project providing compute API support (Level Zero, OpenCL) for Intel graphics hardware architectures (HD Graphics, Xe). -
15
RpiOptimisation
Performance optimization tool for Raspberry Pi.
Support : [Raspberry Pi 0-1-2-3] [EN] Performance optimization tool for Raspberry Pi (CPU,GPU,SD card read and write speed) by model. [FR] Outil d'optimisation des performances pour Raspberry Pi (CPU, GPU, vitesse de lecture et d'écriture de la carte SD) par modèle. -
16
BlockSparse
Efficient GPU kernels for block-sparse matrix multiplication
The blocksparse repository provides efficient GPU kernels (TensorFlow custom ops) for block-sparse matrix multiplication and convolution operations. The idea is to exploit block-level sparsity — i.e. treat matrices or weight tensors as composed of blocks, many of which may be zero or unused — to save compute and memory when sparsity patterns are structured. This is particularly useful in models like Sparse Transformers, where attention matrices or intermediate layers may adopt block-sparse patterns to scale better. ... -
17
Early version of Manjaro-Arm (experimental) with a Mate desktop for Raspberry Pi 2/3 is ready for testing. Just like Lxqt, this edition is based on Manjaro-Arm 16.08 Minimal. Except for standard GPU and sound drivers it contains a set of basic applications: DE - Mate 1.16 (Gtk2) Display Manager - Lxdm Internet - Firefox, x11vnc Multimedia - Kodi (works on click ;) ) Apps - Mate basic applications (Atril, Engrampa, Eol, Mate-terminal...) (Pamac and xscreensaver are not added intentionally - waste of system resources) Others: - GPU change from 64 MB to 192 MB - Auto-login to the system - Automatic installation of external devices - Optimization of themes, icons, widgets and fonts - Remote communication: SSH: sudo ssh manjaro@ip_adress VNC: sudo x11vnc --display :0 -auth guess
-
18
IL1R TILRR FlameGPU
Agent based model of IL1R1 signalling for FLAME GPU
Agent based model of IL1R1 signalling pathway including the co-receptor TILRR. Model File and Functions file for use with FLAME GPU. Example 0.xml starting iteration file included. -
19
HyCuda
Hybrid Framework Generator for CUDA
...Based on a specification file that describes some properties of the algorithm, HyCuda generates C++11 header- and sourcefiles, only a few of which have to be modified by the programmer in order to implement the algorithm itself. The generated code contains a lot of template metaprogramming (TMP), to make sure the decision for an algorithm to run on the CPU or GPU has already been made at compile-time. The same holds for the decisions whether or not to transfer data. This amounts to 0 runtime overhead. -
20
sinestesia
Displays music using fractal flames and hardware acceleration (openCL)
This program takes audio input from microphone, you can redirect pc audio output using control panel on Windows or pavucontrol on Linux. Your computer needs to support openCL (is sufficient a modern gpu or a intel core cpu) Commands: F11 toggle fullscreen S toggle stroboscopic flash NUMBER [0 to 9] change number of symmetry axes -
21
broodKernel
Latest i9001 stock kernel, heavily tweaked!
broodKernel is a kernel that is always based on the latest i9001 kernel, the big difference between an other custom kernel is that broodKernel keeps the original zImage. This means that all stock features are available, in order to tweak it I added a lot of tweaks to the kernels ramdisk. next to the ramdisk tweaks there are 2 init.d scripts which allow you to manage broodKernel the way you want. Visit the github here: https://github.com/broodplank/broodKernel -
22
-
23
granite-timeseries-ttm-r2
Tiny pre-trained IBM model for multivariate time series forecasting
...Unlike massive foundation models, TTM models are designed to be lightweight yet powerful, with only ~805K parameters, enabling high performance even on CPU or single-GPU machines. The r2 version is pre-trained on ~700M samples (r2.1 expands to ~1B), delivering up to 15% better accuracy than the r1 version. TTM supports both zero-shot and fine-tuned forecasting, handling minutely, hourly, daily, and weekly resolutions. It can integrate exogenous variables, static categorical features, and perform channel-mixing for richer multivariate forecasting. ...
