Search Results for "performance" - Page 2
Sort By:
Showing 198 open source projects for "performance"
View related business solutions-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
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
Angel
A Flexible and Powerful Parameter Server for large-scale ML
Angel is a high-performance distributed machine learning and graph computing platform based on the philosophy of Parameter Server. It is tuned for performance with big data from Tencent and has a wide range of applicability and stability, demonstrating an increasing advantage in handling higher-dimension models. Angel is jointly developed by Tencent and Peking University, taking account of both high availability in industry and innovation in academia. -
2
x-transformers
A simple but complete full-attention transformer
A simple but complete full-attention transformer with a set of promising experimental features from various papers. Proposes adding learned memory key/values prior to attending. They were able to remove feedforwards altogether and attain a similar performance to the original transformers. I have found that keeping the feedforwards and adding the memory key/values leads to even better performance. Proposes adding learned tokens, akin to CLS tokens, named memory tokens, that is passed through the attention layers alongside the input tokens. You can also use the l2 normalized embeddings proposed as part of fixnorm. ... -
3
Gen.jl
A general-purpose probabilistic programming system
...But it also lets users migrate parts of their model or inference algorithm to specialized modeling languages for which it can generate especially fast code. Users can also hand-code parts of their models that demand better performance. Neural network inference is fast, but can be inaccurate on out-of-distribution data, and requires expensive training. -
4
Evaluate
A library for easily evaluating machine learning models and datasets
Evaluate is a library that makes evaluating and comparing models and reporting their performance easier and more standardized. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
MLX Engine
LM Studio Apple MLX engine
...Built on top of the mlx-lm and mlx-vlm ecosystems, the engine provides a unified architecture capable of supporting both text-only and multimodal models. Its design focuses on high-performance on-device inference, leveraging Apple’s MLX stack to accelerate computation on M-series chips. The project introduces modular VisionAddOn components that allow image embeddings to be integrated seamlessly into language model workflows. It is bundled with newer versions of LM Studio but can also be used independently for experimentation and development. ... -
6
ANE Training
Training neural networks on Apple Neural Engine via APIs
...It explores the internal software stack of the Apple Neural Engine by interfacing with private classes such as _ANEClient and compiling custom compute graphs in the MIL format. The project includes performance benchmarks and kernel breakdowns that show how different components of the training loop are distributed between the ANE and CPU. It is primarily intended as a research and educational proof of concept rather than a production library, highlighting what is technically possible with undocumented hardware access. -
7
LiteRT-LM
LiteRT-LM is Google's production-ready inference framework
LiteRT-LM is Google’s open-source inference framework for deploying large language models on edge devices. It is built for production-oriented local LLM execution across Android, iOS, desktop, web, embedded, and IoT environments. The framework focuses on performance, hardware acceleration, and efficient model serving close to the user instead of relying only on remote cloud inference. It supports CPU execution across major platforms and adds GPU or NPU acceleration where available. LiteRT-LM is especially relevant for developers building private, low-latency AI features on phones, laptops, Raspberry Pi-style devices, and other edge hardware. ... -
8
imgclsmob Deep learning networks
Sandbox for training deep learning networks
...It includes implementations of models used for tasks such as image classification, object detection, semantic segmentation, and pose estimation. The repository also contains scripts that help train models, evaluate performance, and convert trained networks between different frameworks. Several deep learning frameworks are supported, allowing researchers to experiment with architectures in different environments. The project is frequently used by developers who want to study modern convolutional neural network designs and compare their performance across datasets. -
9
Burn
Burn is a new comprehensive dynamic Deep Learning Framework
Burn is a new comprehensive dynamic Deep Learning Framework from Tracel AI built using Rust with extreme flexibility, compute efficiency and portability as its primary goals. Burn emphasizes performance, flexibility, and portability for both training and inference. Developed in Rust, it is designed to empower machine learning engineers and researchers across industry and academia. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
10
TensorFlow Quantum
Open-source Python framework for hybrid quantum-classical ml learning
...TensorFlow Quantum integrates with the Cirq quantum computing framework to define and manipulate quantum circuits, while leveraging TensorFlow’s infrastructure for optimization, automatic differentiation, and large-scale computation. The library also supports high-performance simulation of quantum circuits, enabling researchers to test and evaluate quantum models even without direct access to quantum hardware. -
11
OpenVINO Notebooks
Jupyter notebook tutorials for OpenVINO
...The repository provides practical tutorials that guide developers through various AI workflows including computer vision, natural language processing, and generative AI tasks. Each notebook demonstrates how to run pre-trained models, optimize inference performance, and deploy models across hardware such as CPUs, GPUs, and specialized accelerators. The tutorials also illustrate how OpenVINO integrates with models from frameworks like PyTorch, TensorFlow, and ONNX to accelerate inference workloads. Many notebooks include end-to-end examples that show how to prepare input data, load optimized models, run inference, and visualize results. ... -
12
Vearch
A distributed system for embedding-based vector retrieval
Vearch is the vector search infrastructure for deep learning and AI applications. Vearch is a distributed vector storage and retrieval system which can be easily extended to billions scale. Vearch implements a high-performance, lockless real-time vector indexing subsystem that utilizes various optimization techniques to support millisecond vector update and retrieval. End-to-end one-click deployment. Through the module of the plugin, a complete default visual search system can be deployed just with one click. Otherwise, you can easily customize your own image, video, or text feature extraction algorithm plugin. ... -
13
Colossal-AI
Making large AI models cheaper, faster and more accessible
The Transformer architecture has improved the performance of deep learning models in domains such as Computer Vision and Natural Language Processing. Together with better performance come larger model sizes. This imposes challenges to the memory wall of the current accelerator hardware such as GPU. It is never ideal to train large models such as Vision Transformer, BERT, and GPT on a single GPU or a single machine. -
14
TensorFlow Serving
Serving system for machine learning models
TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. It deals with the inference aspect of machine learning, taking models after training and managing their lifetimes, providing clients with versioned access via a high-performance, reference-counted lookup table. TensorFlow Serving provides out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data. ... -
15
Gradio
Create UIs for your machine learning model in Python in 3 minutes
Gradio is the fastest way to demo your machine learning model with a friendly web interface so that anyone can use it, anywhere! Gradio can be installed with pip. Creating a Gradio interface only requires adding a couple lines of code to your project. You can choose from a variety of interface types to interface your function. Gradio can be embedded in Python notebooks or presented as a webpage. A Gradio interface can automatically generate a public link you can share with colleagues that... -
16
DVC Extension for Visual Studio Code
https://github.com/iterative/vscode-dvc
A Visual Studio Code extension that integrates Data Version Control (DVC) into the development environment, enhancing reproducibility and collaboration for machine learning projects. -
17
ggml
Tensor library for machine learning
...Written primarily in C and C++, the library provides low-level tensor operations and automatic differentiation that allow developers to implement machine learning algorithms and neural networks efficiently. The project emphasizes portability and performance, enabling machine learning inference across a wide range of hardware environments including CPUs and specialized accelerators. It is widely used as a foundational component in projects that run large language models locally, including tools that perform inference for transformer-based models. The library also implements optimization algorithms and computation graph functionality so developers can build training and inference workflows directly on top of its tensor operations. -
18
ExecuTorch
On-device AI across mobile, embedded and edge for PyTorch
ExecuTorch is an end-to-end solution for enabling on-device inference capabilities across mobile and edge devices including wearables, embedded devices and microcontrollers. It is part of the PyTorch Edge ecosystem and enables efficient deployment of PyTorch models to edge devices. -
19
TensorFlow
TensorFlow is an open source library for machine learning
...TensorFlow expresses its computations as dataflow graphs, with each node in the graph representing an operation. Nodes take tensors—multidimensional arrays—as input and produce tensors as output. The framework allows for these algorithms to be run in C++ for better performance, while the multiple levels of APIs let the user determine how high or low they wish the level of abstraction to be in the models produced. Tensorflow can also be used for research and production with TensorFlow Extended. -
20
Transformer Engine
A library for accelerating Transformer models on NVIDIA GPUs
Transformer Engine (TE) is a library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference. TE provides a collection of highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that can be used seamlessly with your framework-specific code. TE also includes a framework-agnostic C++ API that can be integrated with other deep-learning libraries to enable FP8 support for Transformers. ... -
21
dlib
Toolkit for making machine learning and data analysis applications
Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems. It is used in both industry and academia in a wide range of domains including robotics, embedded devices, mobile phones, and large high performance computing environments. Dlib's open source licensing allows you to use it in any application, free of charge. Good unit test coverage, the ratio of unit test lines of code to library lines of code is about 1 to 4. The library is tested regularly on MS Windows, Linux, and Mac OS X systems. No other packages are required to use the library, only APIs that are provided by an out of the box OS are needed. ... -
22
caret
caret (Classification And Regression Training) R package
The caret (Classification And Regression Training) R package streamlines the process of building predictive machine learning models. It provides uniform interfaces for model training, tuning, evaluation, preprocessing, and variable importance. With support for over 200 models, caret is foundational for R workflows in modeling and machine learning. -
23
TensorFlow Datasets
TFDS is a collection of datasets ready to use with TensorFlow,
TensorFlow Datasets is a collection of datasets ready to use, with TensorFlow or other Python ML frameworks, such as Jax. All datasets are exposed as tf.data. Datasets , enabling easy-to-use and high-performance input pipelines. To get started see the guide and our list of datasets. -
24
Smile
Statistical machine intelligence and learning engine
Smile is a fast and comprehensive machine learning engine. With advanced data structures and algorithms, Smile delivers the state-of-art performance. Compared to this third-party benchmark, Smile outperforms R, Python, Spark, H2O, xgboost significantly. Smile is a couple of times faster than the closest competitor. The memory usage is also very efficient. If we can train advanced machine learning models on a PC, why buy a cluster? Write applications quickly in Java, Scala, or any JVM languages. ... -
25
shimmy
Python-free Rust inference server
...This compatibility enables developers to replace remote AI services with locally hosted models while keeping their existing software architecture intact. Shimmy focuses on performance and simplicity, using efficient runtime components to minimize memory usage and startup time compared to heavier inference frameworks. It supports modern model formats such as GGUF and SafeTensors and can automatically discover models stored locally or in common directories used by other AI tools. Advanced capabilities include CPU offloading for Mixture-of-Experts models and GPU acceleration, enabling large models to run on consumer hardware with limited VRAM.
