Search Results for "speed-dreeams"
Sort By:
Showing 272 open source projects for "speed-dreeams"
View related business solutions-
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.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
1
Neural Speed
An innovative library for efficient LLM inference
neural-speed is an innovative library developed by Intel to enhance the efficiency of Large Language Model (LLM) inference through low-bit quantization techniques. By reducing the precision of model weights and activations, neural-speed aims to accelerate inference while maintaining model accuracy, making it suitable for deployment in resource-constrained environments. -
2
pgvector
Open-source vector similarity search for Postgres
pgvector is an open-source PostgreSQL extension that equips PostgreSQL databases with vector data storage, indexing, and similarity search capabilities—ideal for embeddings-based applications like semantic search and recommendations. You can add an index to use approximate nearest neighbor search, which trades some recall for speed. Unlike typical indexes, you will see different results for queries after adding an approximate index. An HNSW index creates a multilayer graph. It has better query performance than IVFFlat (in terms of speed-recall tradeoff), but has slower build times and uses more memory. Also, an index can be created without any data in the table since there isn’t a training step like IVFFlat. -
3
llmfit
157 models, 30 providers, one command to find what runs on hardware
llmfit is a terminal-based utility that helps developers determine which large language models can realistically run on their local hardware by analyzing system resources and model requirements. The tool automatically detects CPU, RAM, GPU, and VRAM specifications, then ranks available models based on performance factors such as speed, quality, and memory fit. It provides both an interactive terminal user interface and a traditional CLI mode, enabling flexible workflows for different user preferences. llmfit also supports advanced configurations including multi-GPU setups, mixture-of-experts architectures, and dynamic quantization recommendations. By presenting clear performance estimates and compatibility guidance, the project reduces the trial-and-error typically involved in local LLM experimentation. ... -
4
Faster Whisper
Faster Whisper transcription with CTranslate2
...The system is particularly useful for real-time or large-scale transcription tasks where performance is critical. It supports multiple model sizes, allowing users to balance speed and accuracy based on their needs. The architecture is designed to run efficiently on both CPUs and GPUs, making it accessible across different environments. It also includes support for streaming and batch processing, enabling flexible deployment scenarios. Overall, faster-whisper makes state-of-the-art speech recognition more practical for production use cases by improving speed and efficiency without sacrificing quality. -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
WhisperX
Automatic Speech Recognition with Word-level Timestamps
...It addresses key limitations of standard Whisper implementations by introducing voice activity detection and forced alignment techniques to produce word-level timestamps. The system enables batched inference, significantly increasing transcription speed while maintaining high accuracy. It is particularly effective for long recordings, where traditional approaches may suffer from drift, repetition, or misalignment. whisperx also supports speaker diarization, allowing identification of different speakers within a conversation. Its architecture combines multiple components to enhance both performance and usability in real-world transcription tasks. ... -
6
MiniCPM4.1
Achieving 3+ generation speedup on reasoning tasks
MiniCPM4.1 is an enhanced iteration of the MiniCPM4 architecture, introducing improvements in reasoning capabilities, inference speed, and hybrid operation modes that allow dynamic switching between deep reasoning and standard generation. It builds upon the same efficiency-focused philosophy but further optimizes decoding performance, achieving substantial speed gains in reasoning-intensive tasks while maintaining high-quality outputs. One of its key innovations is the hybrid reasoning mode, which allows developers to control whether the model engages in deeper reasoning processes or faster responses depending on the use case. ... -
7
PyTorch
Open source machine learning framework
...PyTorch consists of torch (Tensor library), torch.autograd (tape-based automatic differentiation library), torch.jit (a compilation stack [TorchScript]), torch.nn (neural networks library), torch.multiprocessing (Python multiprocessing), and torch.utils (DataLoader and other utility functions). PyTorch can be used as a replacement for Numpy, or as a deep learning research platform that provides optimum flexibility and speed. -
8
Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models
...Because it’s part of the broader Qwen ecosystem, it benefits from the model’s understanding of linguistic nuances, enabling more accurate pronunciation, prosody, and contextual delivery than many traditional TTS systems. Developers can customize voice output parameters like speed, pitch, and volume, and combine the TTS stack with other AI components. -
9
Distributed Llama
Connect home devices into a powerful cluster to accelerate LLM
Distributed Llama is an open-source project that enables users to connect multiple home devices into a powerful cluster to accelerate Large Language Model (LLM) inference. By leveraging tensor parallelism and high-speed synchronization over Ethernet, it allows for faster performance as more devices are added to the cluster. The system supports various operating systems, including Linux, macOS, and Windows, and is optimized for both ARM and x86_64 AVX2 CPUs. -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
Perplexica
Perplexica is an AI-powered answering engine.
...It combines live internet search results with AI models, letting you use local LLMs via Ollama or connect to providers like OpenAI, Claude, Gemini, and Groq. Powered by SearxNG, it aggregates results from multiple search engines while keeping your identity and queries private. Perplexica offers multiple search modes—Speed, Balanced, and Quality—so you can trade off latency and depth depending on the task. It also enhances the experience with widgets and rich search types like images, videos, and domain-limited queries. With local search history, file uploads, and an easy Docker-based setup, it’s built for everyday research without sacrificing control or privacy. -
11
PowerInfer
High-speed Large Language Model Serving for Local Deployment
...Its architecture exploits the observation that only a subset of neurons in large models are frequently activated, allowing the system to preload frequently used neurons into GPU memory while processing less common activations on the CPU. This hybrid execution strategy significantly reduces memory bottlenecks and improves overall inference speed. PowerInfer incorporates specialized algorithms and sparse operators to manage neuron activation patterns and minimize data transfers between hardware components. As a result, it enables powerful language models to run on consumer hardware while achieving performance comparable to more expensive server-grade systems. -
12
LightGBM
Gradient boosting framework based on decision tree algorithms
LightGBM or Light Gradient Boosting Machine is a high-performance, open source gradient boosting framework based on decision tree algorithms. Compared to other boosting frameworks, LightGBM offers several advantages in terms of speed, efficiency and accuracy. Parallel experiments have shown that LightGBM can attain linear speed-up through multiple machines for training in specific settings, all while consuming less memory. LightGBM supports parallel and GPU learning, and can handle large-scale data. It’s become widely-used for ranking, classification and many other machine learning tasks. -
13
Wanaku
Wanaku MCP Router
Wanaku is an MCP Router designed to connect AI-enabled applications using the Model Context Protocol. Built on top of Apache Camel and Quarkus, it offers unmatched connectivity, speed, and reliability for AI agents, facilitating seamless integration across various services and platforms. -
14
Amical
Open Source AI Dictation App
Amical is an open source, AI-powered desktop dictation and note-taking application that enables users to dictate hands-free, transcribe meetings, and capture notes effortlessly with unmatched speed, accuracy, and privacy. It leverages both local and cloud-based AI models, letting users seamlessly switch between providers for the ideal balance of speed, precision, and control, and understands the context of each app in use to automatically format text in a tone and style appropriate to the platform. Users can enhance transcription accuracy with custom vocabulary tailored to industry jargon, proper nouns, and personal terms, and set up personalized voice shortcuts to trigger workflows or dictate across applications. ... -
15
model2Vec
Fast State-of-the-Art Static Embeddings
model2vec is an innovative embedding framework that converts large sentence transformer models into compact, high-speed static embedding models while preserving much of their semantic performance. The project focuses on dramatically reducing the computational cost of generating embeddings, achieving significant improvements in speed and model size without requiring large datasets for retraining. By using a distillation-based approach, it can produce lightweight models that run efficiently on CPUs, making it suitable for edge applications and large-scale processing pipelines. ... -
16
Qdrant
Vector Database for the next generation of AI applications
...Alternatively, utilize ready-made client for Python or other programming languages with additional functionality. Implement a unique custom modification of the HNSW algorithm for the Approximate Nearest Neighbor Search. Search with a State-of-the-Art speed and apply search filters without compromising on results. Support additional payload associated with vectors. Not only stores payload but also allows filter results based on payload values. Unlike Elasticsearch post-filtering, Qdrant guarantees all relevant vectors are retrieved. -
17
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
...The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU memory usage / improve efficiency. Parallel inference code to speed up sampling, utilities and tests included. -
18
TurboDiffusion
100–200× Acceleration for Video Diffusion Models
...The project targets large video models and enables developers to run accelerated generation even on single high-end GPUs, making fast video synthesis more practical for research and creative workflows. TurboDiffusion is structured to integrate with existing diffusion model architectures and provides tools for experimenting with and benchmarking speed and quality trade-offs. -
19
HunyuanWorld-Mirror
Fast and Universal 3D reconstruction model for versatile tasks
...The model accepts combinations of images, camera intrinsics and poses, or even depth cues, then reconstructs consistent 3D geometry suitable for downstream rendering or editing. The pipeline emphasizes both speed and flexibility so creators can go from casual captures to assets without elaborate capture rigs. Outputs can include point clouds, estimated camera parameters, and other 3D representations that plug into typical graphics workflows. The project sits within a broader family of Hunyuan models that explore world generation and 3D-consistent understanding, and this mirror variant makes the reconstruction stack easier to test. ... -
20
CatBoost
High-performance library for gradient boosting on decision trees
...It is a machine learning method with plenty of applications, including ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. CatBoost offers superior performance over other GBDT libraries on many datasets, and has several superb features. It has best in class prediction speed, supports both numerical and categorical features, has a fast and scalable GPU version, and readily comes with visualization tools. CatBoost was developed by Yandex and is used in various areas including search, self-driving cars, personal assistance, weather prediction and more. -
21
LightRAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
LightRAG is a lightweight Retrieval-Augmented Generation (RAG) framework designed for efficient document retrieval and response generation. It is optimized for speed and lower resource consumption, making it ideal for real-time applications. -
22
MiniCPM4
Ultra-Efficient LLMs on End Device
...The model demonstrates strong performance across tasks such as long-text comprehension, reasoning, and general language generation, often outperforming similar-sized models in both speed and accuracy. MiniCPM4 is available in multiple parameter sizes, making it adaptable to different deployment scenarios ranging from mobile devices to GPUs. -
23
ACE-Step 1.5
The most powerful local music generation model
ACE-Step 1.5 is an advanced open-source foundation model for AI-driven music generation that pushes beyond traditional limitations in speed, musical coherence, and controllability by innovating in architecture and training design. It integrates cutting-edge generative techniques—such as diffusion-based synthesis combined with compressed autoencoders and lightweight transformer elements—to produce high-quality full-length music tracks with rapid inference times, capable of generating a complete song in seconds on modern GPUs while remaining efficient enough to run on consumer-grade hardware with minimal memory requirements. ... -
24
YOLOv5
YOLOv5 is the world's most loved vision AI
Introducing Ultralytics YOLOv8, the latest version of the acclaimed real-time object detection and image segmentation model. YOLOv8 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy. Its streamlined design makes it suitable for various applications and easily adaptable to different hardware platforms, from edge devices to cloud APIs. Explore the YOLOv8 Docs, a comprehensive resource designed to help you understand and utilize its features and capabilities. Whether you are a seasoned machine learning practitioner or new to the field, this hub aims to maximize YOLOv8's potential in your projects. -
25
Ultralytics
Ultralytics YOLO
...The framework supports a full end-to-end workflow, including dataset preparation, model training, evaluation, and export to various deployment formats. Its architecture emphasizes performance optimization, balancing speed and accuracy to support real-time applications across industries. Ultralytics also provides pretrained models and flexible configuration options, allowing users to adapt the system to different datasets and use cases with minimal effort.
