Search Results for "memory"
Sort By:
Showing 60 open source projects for "memory"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
1
whisper.cpp
Port of OpenAI's Whisper model in C/C++
...The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently. -
2
ncnn
High-performance neural network inference framework for mobile
ncnn is a high-performance neural network inference computing framework designed specifically for mobile platforms. It brings artificial intelligence right at your fingertips with no third-party dependencies, and speeds faster than all other known open source frameworks for mobile phone cpu. ncnn allows developers to easily deploy deep learning algorithm models to the mobile platform and create intelligent APPs. It is cross-platform and supports most commonly used CNN networks, including... -
3
bitnet.cpp
Official inference framework for 1-bit LLMs
bitnet.cpp is the official open-source inference framework and ecosystem designed to enable ultra-efficient execution of 1-bit large language models (LLMs), which quantize most model parameters to ternary values (-1, 0, +1) while maintaining competitive performance with full-precision counterparts. At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous compute infrastructure. The project’s focus on extreme quantization dramatically reduces memory footprint and energy consumption compared with traditional 16-bit or 32-bit LLMs, making it practical to deploy advanced language understanding and generation models on everyday machines. ... -
4
TensorFlow Lite for Microcontrollers
Infrastructure to enable deployment of ML models
TensorFlow Lite for Microcontrollers is a TensorFlow Lite runtime designed for running machine learning models on tiny embedded devices. It targets microcontrollers, DSPs, and other resource-constrained hardware where memory, compute, and power are limited. The project enables on-device inference without depending on an operating system, standard C or C++ libraries, or dynamic memory allocation. It is useful for applications such as wake-word detection, sensor analysis, gesture recognition, anomaly detection, and small vision or audio models. Developers can train or convert models into TensorFlow Lite format and deploy them into embedded firmware. ... -
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
5
Operit AI
Powerful Android AI agent with tools, automation, and Linux shell
...Operit supports both local and remote AI models, including offline execution through frameworks like llama.cpp and MNN, helping preserve user privacy while maintaining flexibility. Operit also includes an intelligent memory system that stores, organizes, and retrieves user interactions to provide more personalized and context-aware responses. In addition, it offers workflow automation, plugin extensibility, & a rich tool ecosystem, making it suitable for advanced productivity. -
6
Mooncake
Mooncake is the serving platform for Kimi
...Its architecture centers on a high-performance transfer engine that provides unified data transfer across different storage and networking technologies. This engine enables efficient movement of tensors and model data across heterogeneous environments such as GPU memory, system memory, and distributed storage systems. Mooncake also introduces distributed key-value cache storage that allows inference systems to reuse previously computed attention states, significantly improving throughput in large-scale deployments. The system supports advanced networking technologies such as RDMA and NVMe over Fabric, enabling high-speed communication across clusters. -
7
CTranslate2
Fast inference engine for Transformer models
...The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). ... -
8
FlashMLA
FlashMLA: Efficient Multi-head Latent Attention Kernels
...It provides optimized kernels for MLA decoding, including support for variable-length sequences, helping reduce latency and increase throughput in model inference systems using that attention style. The library supports both BF16 and FP16 data types, and includes a paged KV cache implementation with a block size of 64 to efficiently manage memory during decoding. On very compute-bound settings, it can reach up to ~660 TFLOPS on H800 SXM5 hardware, while in memory-bound configurations it can push memory throughput to ~3000 GB/s. The team regularly updates it with performance improvements; for example, a 2025 update claims 5 % to 15 % gains on compute-bound workloads while maintaining API compatibility. -
9
LightGBM
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. -
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.
-
10
Pedalboard
A Python library for audio
pedalboard is a Python library for working with audio: reading, writing, rendering, adding effects, and more. It supports the most popular audio file formats and a number of common audio effects out of the box and also allows the use of VST3® and Audio Unit formats for loading third-party software instruments and effects. pedalboard was built by Spotify’s Audio Intelligence Lab to enable using studio-quality audio effects from within Python and TensorFlow. Internally at Spotify, pedalboard... -
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
Cactus
Low-latency AI inference engine optimized for mobile devices
...It provides a full-stack architecture composed of an inference engine, a computation graph system, and highly optimized hardware kernels tailored for ARM-based processors. Cactus emphasizes efficient memory usage through techniques such as zero-copy computation graphs and quantized model formats, allowing large models to run within the constraints of mobile hardware. It supports a wide range of AI tasks including text generation, speech-to-text, vision processing, and retrieval-augmented workflows through a unified API interface. A notable feature of Cactus is its hybrid execution model, which can dynamically route tasks between on-device processing and cloud services when additional compute is required. -
13
ChatGLM.cpp
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
ChatGLM.cpp is a C++ implementation of the ChatGLM-6B model, enabling efficient local inference without requiring a Python environment. It is optimized for running on consumer hardware. -
14
tt-metal
TT-NN operator library, and TT-Metalium low level kernel programming
...Instead of following a traditional GPU model centered on massive thread parallelism, the platform is built around a grid of specialized compute nodes called Tensix cores, each with local SRAM, dedicated compute units, and multiple RISC-V control processors. The SDK provides the abstractions and APIs needed to manage data movement, compute kernels, memory coordination, and execution flow across this architecture. -
15
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,... -
16
llama.cpp
LLM inference in C/C++
llama.cpp is a high-performance C and C++ project for running large language models locally and in the cloud with minimal setup. It is built around efficient inference, broad hardware support, and the GGUF model format. The project supports many model families and has become a major foundation for local AI tools, model serving, and embedded inference workflows. It provides command-line tools, a server mode with an OpenAI-compatible API style, model conversion utilities, and extensive backend... -
17
Bolt NLP
Bolt is a deep learning library with high performance
Bolt is a high-performance deep learning inference framework developed by Huawei Noah's Ark Lab. It is designed to optimize and accelerate the deployment of deep learning models across various hardware platforms. Bolt is a light-weight library for deep learning. Bolt, as a universal deployment tool for all kinds of neural networks, aims to automate the deployment pipeline and achieve extreme acceleration. Bolt has been widely deployed and used in many departments of HUAWEI company, such as... -
18
RTP-LLM
Alibaba's high-performance LLM inference engine for diverse apps
...The system focuses on improving throughput, latency, and resource utilization when running large models in production environments. It achieves this by implementing optimized GPU kernels, batching strategies, and memory management techniques tailored for transformer inference workloads. The framework is designed for large-scale AI services and is already used internally across several Alibaba platforms such as Taobao, Amap, and other business systems that rely on conversational or search-related AI services. RTP-LLM supports a wide variety of modern model architectures, including Qwen, DeepSeek, and Llama-based models, making it a flexible engine for deploying many different open-source LLMs. -
19
LiteRT
LiteRT, successor to TensorFlow Lite
...LiteRT supports a wide range of platforms, including Android, iOS, Linux, macOS, Windows, web environments, and IoT devices. The framework simplifies on-device AI development through automated accelerator selection, asynchronous execution, and optimized memory handling. It also includes specialized support for large language models and generative AI workloads through LiteRT-LM and related tooling. With broad hardware compatibility and advanced performance optimizations, LiteRT enables developers to build fast, scalable, and efficient AI applications that run directly on user devices. -
20
nndeploy
An Easy-to-Use and High-Performance AI Deployment Framework
...The system supports multiple inference engines and hardware accelerators, allowing the same AI workflow to run on different platforms without significant modifications. nndeploy also includes performance optimization techniques such as parallel execution, memory reuse, and hardware-accelerated operations to improve inference speed. -
21
ArrayFire
ArrayFire, a general purpose GPU library
ArrayFire is a general-purpose tensor library that simplifies the process of software development for the parallel architectures found in CPUs, GPUs, and other hardware acceleration devices. The library serves users in every technical computing market. Data structures in ArrayFire are smartly managed to avoid costly memory transfers and to take advantage of each performance feature provided by the underlying hardware. The community of ArrayFire developers invites you to build with us if you're interested and able to write top performing tensor functions. Together we can fulfill The ArrayFire Mission under an excellent Code of Conduct that promotes a respectful and friendly building experience. ... -
22
Tiny CUDA Neural Networks
Lightning fast C++/CUDA neural network framework
...We provide a sample application where an image function (x,y) -> (R,G,B) is learned. The fully fused MLP component of this framework requires a very large amount of shared memory in its default configuration. It will likely only work on an RTX 3090, an RTX 2080 Ti, or high-end enterprise GPUs. Lower-end cards must reduce the n_neurons parameter or use the CutlassMLP (better compatibility but slower) instead. tiny-cuda-nn comes with a PyTorch extension that allows using the fast MLPs and input encodings from within a Python context. ... -
23
qvac-fabric-llm.cpp
QVAC Fabric: cross-platform LLM inference and fine-tuning
qvac-fabric-llm.cpp is a cross-platform large language model inference and fine-tuning engine built as an advanced fork of llama.cpp, designed to run efficiently across desktops, mobile devices, and heterogeneous GPU environments. The project focuses on removing hardware limitations traditionally associated with LLM deployment by enabling support for a wide range of backends, including Vulkan, Metal, CUDA, and CPU, making it accessible on devices ranging from smartphones to enterprise... -
24
MegEngine
Easy-to-use deep learning framework with 3 key features
...After training, just put everything into your model and inference it on any platform at ease. Speed and precision problems won't bother you anymore due to the same core inside. In training, GPU memory usage could go down to one-third at the cost of only one additional line, which enables the DTR algorithm. Gain the lowest memory usage when inferencing a model by leveraging our unique pushdown memory planner. NOTE: MegEngine now supports Python installation on Linux-64bit/Windows-64bit/MacOS(CPU-Only)-10.14+/Android 7+(CPU-Only) platforms with Python from 3.5 to 3.8. ... -
25
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.
