Search Results for "gpu turbo boost"
Sort By:
Showing 33 open source projects for "gpu turbo boost"
View related business solutions-
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.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
GPU-Z
Lightweight GPU information and diagnostics tool.
...It accurately reports clock speeds, including default, overclocked, 3D, and boost clocks. Furthermore, it provides a detailed analysis of the memory subsystem, including size, type, speed, and bus width. Unique features include a GPU load test to verify PCI-Express configuration, results validation, and the ability to back up your graphics card BIOS. It is portable (requires no installation) and fully supports all modern Windows versions, including Windows 11. -
2
CoreCycler
Script to test single core stability
...With this script, you can test the stability for each core, which helps you to validate if your Ryzen "PBO" resp. "Curve Optimizer" settings are actually stable. It also works to test Intel's "Active-Core" Turbo-Boost settings. -
3
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
LMCache is an extension layer for LLM serving engines that accelerates inference, especially with long contexts, by storing and reusing key-value (KV) attention caches across requests. Instead of rebuilding KV states for repeated or shared text segments, LMCache persists and retrieves them from multiple tiers—GPU memory, CPU DRAM, and local disk—then injects them into subsequent requests to reduce TTFT and increase throughput. Its design supports reuse beyond strict prefix matching and... -
4
Zed
High-performance, multiplayer code editor from the creators of Atom
...Fast native terminal tightly integrates with Zed's language-aware task runner and AI capabilities. First-class modal editing via Vim bindings, including features like text objects and marks. Zed is built by a global community of thousands of developers. Boost your Zed experience by choosing from hundreds of extensions that broaden language support, offer different themes, and more. -
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
5
OpenVINO
OpenVINO™ Toolkit repository
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference. Boost deep learning performance in computer vision, automatic speech recognition, natural language processing and other common tasks. Use models trained with popular frameworks like TensorFlow, PyTorch and more. Reduce resource demands and efficiently deploy on a range of Intel® platforms from edge to cloud. This open-source version includes several components: namely Model Optimizer, OpenVINO™ Runtime, Post-Training Optimization Tool, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics. ... -
6
CodeGeeX2
CodeGeeX2: A More Powerful Multilingual Code Generation Model
CodeGeeX2 is the second-generation multilingual code generation model from ZhipuAI, built upon the ChatGLM2-6B architecture and trained on 600B code tokens. Compared to the first generation, it delivers a significant boost in programming ability across multiple languages, outperforming even larger models like StarCoder-15B in some benchmarks despite having only 6B parameters. The model excels at code generation, translation, summarization, debugging, and comment generation, and it supports over 100 programming languages. With improved inference efficiency, quantization options, and multi-query/flash attention, CodeGeeX2 achieves faster generation speeds and lightweight deployment, requiring as little as 6GB GPU memory at INT4 precision. ... -
7
Intel Extension for PyTorch
A Python package for extending the official PyTorch
Intel® Extension for PyTorch* extends PyTorch* with up-to-date features optimizations for an extra performance boost on Intel hardware. Optimizations take advantage of Intel® Advanced Vector Extensions 512 (Intel® AVX-512) Vector Neural Network Instructions (VNNI) and Intel® Advanced Matrix Extensions (Intel® AMX) on Intel CPUs as well as Intel Xe Matrix Extensions (XMX) AI engines on Intel discrete GPUs. Moreover, Intel® Extension for PyTorch* provides easy GPU acceleration for Intel discrete GPUs through the PyTorch* xpu device. -
8
Wan2.2
Wan2.2: Open and Advanced Large-Scale Video Generative Model
Wan2.2 is a major upgrade to the Wan series of open and advanced large-scale video generative models, incorporating cutting-edge innovations to boost video generation quality and efficiency. It introduces a Mixture-of-Experts (MoE) architecture that splits the denoising process across specialized expert models, increasing total model capacity without raising computational costs. Wan2.2 integrates meticulously curated cinematic aesthetic data, enabling precise control over lighting,... -
9
bitResurrector
Bitcoin private key recovery tool with Bloom Filter & CUDA
...The engine exploits specific entropy vulnerabilities (CVE-2013-7372) and uses a 9-echelon statistical filter to segregate mathematical "corpses" from potentially valid keys. Technological Stack: - Zero-Latency Bloom Filter: Real-time matching against 58M+ active addresses (Loyce Club data). - Turbo Core: C++/AVX-512 optimization with processor affinity. - GPU Mode: Massive parallel computation via NVIDIA CUDA. - Memory Management: Zero disk I/O lag using mmap (Memory-Mapped Files). BitResurrector is a closed-source, proprietary tool for researchers and professionals. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
10
TensorRT
C++ library for high performance inference on NVIDIA GPUs
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for deep learning inference applications. TensorRT-based applications perform up to 40X faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and deploy to hyperscale data centers,... -
11
Metro-2039-Boost-fps
Increase FPS in Metro 2039 for smoother gameplay
Metro 2039 Boost fps is a utility designed to optimize performance in the upcoming Metro 2039. It provides several options to improve your framerate and reduce stuttering, resulting in a more enjoyable gaming experience. This tool allows players to adjust graphic settings beyond the in-game limitations. It dynamically optimizes CPU and GPU usage depending on the current scene complexity. -
12
Whisper Turbo
Cross-Platform, GPU Accelerated Whisper
Whisper Turbo is a fast, cross-platform Whisper implementation, designed to run entirely client-side in your browser/electron app. -
13
SmartGaGa
Lightweight Android emulator optimized for FPS games on low-end PCs
SmartGaGa is a free Android emulator optimized for playing mobile games on Windows computers with minimal system requirements. Powered by Titan Engine and Turbo GPU technology, the software delivers smooth gaming performance even on machines with 2GB RAM and dual-core processors. The emulator supports popular FPS titles including Free Fire, PUBG Mobile, Clash of Clans, and Cyber Hunter, enabling players to enjoy mobile games on larger screens with keyboard and mouse controls. SmartGaGa runs Android Nougat natively and integrates Google Play Store for easy app installation, while also supporting APK sideloading for offline installation. ... -
14
MSI Afterburner
MSI Afterburner: Overclock, monitor, and optimize your GPU.
MSI Afterburner is the world's most recognized and widely used graphics card overclocking utility. It provides a comprehensive suite of tools for gamers and PC enthusiasts to enhance their graphics card's performance and monitor its health. With MSI Afterburner, users can overclock their GPU to achieve higher frame rates in games, undervolt to reduce power consumption and heat, and customize fan curves for optimal cooling. The software also includes an on-screen display (OSD) feature that... -
15
Roblox Shaders
Roblox Shader – Download on Any GPU
Roblox Shader – Universal Graphics Enhancement for All GPUs Roblox Shader is a high-performance, universal shader mod designed to enhance Roblox graphics with realistic lighting, shadows, and post-processing effects. This shader pack is optimized for all graphics cards, including NVIDIA, AMD, and Intel GPUs, ensuring compatibility across virtually any system. Whether you're looking to improve Roblox visuals with better lighting or want a more immersive gaming experience, Roblox Shader... -
16
NekoHyperSeed
NekoHyper Seed Modified Xiaomi HyperOS for marble/marblein device
Feature: no binary modification (except OFRP and melt kernel) and only added minimal config file modification needed by feature unlock to keep every thing user-side trusted and reviewable Stable and keep updated to Xiaomi offical You can keep your userdata after each update Unlock features without losing security Telegram Group: https://t.me/nekohyper_official 为中国用户提供的镜像下载站: https://nhs.ykmiog6pbx.cn -
17
Roblox Shaders Master
Roblox Shader – Download for Any GPU
Roblox Shader – Universal Graphics Enhancement for All GPUs Roblox Shader is a high-performance, universal shader mod designed to enhance Roblox graphics with realistic lighting, shadows, and post-processing effects. This shader pack is optimized for all graphics cards, including NVIDIA, AMD, and Intel GPUs, ensuring compatibility across virtually any system. Whether you're looking to improve Roblox visuals with better lighting or want a more immersive gaming experience, Roblox Shader... -
18
AMD APU Tuning Utility
Unlock the full potential of your Zen-based APU with AMD APU Tuning
Universal x86 Tuning Utility is a powerful tool designed to assist users in optimizing the performance and settings of their x86 laptops and computers. Its primary objective is to provide users with the ability to customize and fine-tune their device settings according to their preferences and needs. The development of this utility is spearheaded by the same talented team that brought us popular applications like Ryzen Controller, Renoir Mobile Tuning, and Power Control Panel. Universal x86... -
19
Synaptrix ChatGPT Desktop
Fuel your productivity with ChatGPT-Desktop
Fuel your productivity with ChatGPT-Desktop, blazingly fast and supercharged. -
20
LLaMA.go
llama.go is like llama.cpp in pure Golang
llama.go is like llama.cpp in pure Golang. The code of the project is based on the legendary ggml.cpp framework of Georgi Gerganov written in C++ with the same attitude to performance and elegance. Both models store FP32 weights, so you'll needs at least 32Gb of RAM (not VRAM or GPU RAM) for LLaMA-7B. Double to 64Gb for LLaMA-13B. -
21
NanoDet-Plus
Lightweight anchor-free object detection model
Super fast and high accuracy lightweight anchor-free object detection model. Real-time on mobile devices. NanoDet is a FCOS-style one-stage anchor-free object detection model which using Generalized Focal Loss as classification and regression loss. In NanoDet-Plus, we propose a novel label assignment strategy with a simple assign guidance module (AGM) and a dynamic soft label assigner (DSLA) to solve the optimal label assignment problem in lightweight model training. We also introduce a... -
22
YOLO ROS
YOLO ROS: Real-Time Object Detection for ROS
This is a ROS package developed for object detection in camera images. You only look once (YOLO) is a state-of-the-art, real-time object detection system. In the following ROS package, you are able to use YOLO (V3) on GPU and CPU. The pre-trained model of the convolutional neural network is able to detect pre-trained classes including the data set from VOC and COCO, or you can also create a network with your own detection objects. The YOLO packages have been tested under ROS Noetic and... -
23
Mi A1: LuciferKernel
Linux 4.9 Kernel for Xiaomi Mi A1 aka Tissot
Join official telegram group: https://t.me/luciferkernel Kernel stage Changed to Beta. Features: →Added F2FS Rapid Gc. → CPU OC to 3.1Mhz (OC Build Only) → GPU OC to 850Mhz (OC Build Only) → Reduced GPU idle time to 64ms → Added DTS-Eagle. → CPU undervolted upto 10% → Improved thermals. → Added Sound tweaks. → Added Boeffla Wakelocker → Added State Notifier → Added Adreno Idler → Added Adreno Boost → Added dynamic SchedTune boost. → Added Klapse → Added KCAL → Added BFQ I/O scheduler →Upstreamed to 4.9.232 →Added gcam7+ support (experimental) thanks to @mtpiplod →Fixed certain errors →Built with Proton Clang 12 For Non-OC except Overclocked CPU , GPU and some performance schedulers everything is same -
24
...•Feature On Alive Kernel• -Based on caf kernel linux Stable -Merged with new tag caf latest -OC to 2.2Ghz -Battre Friedly -Better Performance -Add more governor ~Nightmare ~Darknessv5 ~Alucard ~and more -Undervolt Cpu Gpu -80mV -Add Cpu Bost Control and More Control -Add Cpu hotplug -Add Gpu boost -Add New battery Calculation -Add Fast Charging and On/Off Charging -Add Sound Control -Add Kcal Support and more option -Add I/O Tweak and more scheduler -Lmk Optimize (4/6Gb Ram varian) -Add Boeffla Wakelocks -Add WireGuard -Optimize Zram for battery saving -Tcp Algorithm Optimize -Much More
-
25
OpenSeq2Seq
Toolkit for efficient experimentation with Speech Recognition
OpenSeq2Seq is a TensorFlow-based toolkit for efficient experimentation with sequence-to-sequence models across speech and NLP tasks. Its core goal is to give researchers a flexible, modular framework for building and training encoder–decoder architectures while fully leveraging distributed and mixed-precision training. The toolkit includes ready-made models for neural machine translation, automatic speech recognition, speech synthesis, language modeling, and additional NLP tasks such as...
