Search Results for "compression"
Sort By:
Showing 65 open source projects for "compression"
View related business solutions-
The full-stack observability platform that protects your dataLayer, tags and conversion dataCode-Cube.io detects issues instantly, alerts you in real time and helps you resolve them fast. No manual QA. No unreliable data. Just data you can trust and act on.
-
Iris Powered By Generali - Iris puts your customer in control of their identity.Iris Identity Protection API sends identity monitoring and alerts data into your existing digital environment – an ideal solution for businesses that are looking to offer their customers identity protection services without having to build a new product or app from scratch.
-
1
MCP Image Compression
A high-performance image compression microservice based on MCP
The MCP Image Compression server is a high-performance microservice based on the Model Context Protocol architecture. It focuses on providing fast and high-quality image compression capabilities to help developers optimize image resources for websites and applications, improving loading speed and user experience. -
2
DeepSpeed
Deep learning optimization library: makes distributed training easy
...Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme compression for an unparalleled inference latency and model size reduction with low costs DeepSpeed offers a confluence of system innovations, that has made large scale DL training effective, and efficient, greatly improved ease of use, and redefined the DL training landscape in terms of scale that is possible. These innovations such as ZeRO, 3D-Parallelism, DeepSpeed-MoE, ZeRO-Infinity, etc. fall under the training pillar. -
3
NNCF
Neural Network Compression Framework for enhanced OpenVINO
NNCF (Neural Network Compression Framework) is an optimization toolkit for deep learning models, designed to apply quantization, pruning, and other techniques to improve inference efficiency. -
4
Wan2.2
Wan2.2: Open and Advanced Large-Scale Video Generative Model
...The model is trained on significantly larger datasets than its predecessor, greatly enhancing motion complexity, semantic understanding, and aesthetic diversity. Wan2.2 also open-sources a 5-billion parameter high-compression VAE-based hybrid text-image-to-video (TI2V) model that supports 720P video generation at 24fps on consumer-grade GPUs like the RTX 4090. It supports multiple video generation tasks including text-to-video. -
Inventory and Order Management Software for Multichannel SellersWe are the most powerful inventory and order management platform for Amazon, Walmart, and multichannel product sellers. Centralize orders, product information, and fulfillment operations to run more efficiently, sell more products, and stay compliant with marketplace requirements so you can grow profitably.
-
5
LLM Action
Technical principles related to large models
LLM-Action is a knowledge/tutorial/repository that shares principles, techniques, and real-world experience related to large language models (LLMs), focusing on LLM engineering, deployment, optimization, inference, compression, and tooling. It organizes content in domains like training, inference, compression, alignment, evaluation, pipelines, and applications. Sections covering infrastructure, engineering, and deployment. Repository templates, sample code, and resource links. Articles/code on LLM compression (quantization, pruning). -
6
MemPalace
The highest-scoring AI memory system ever benchmarked
...It operates fully locally using tools like ChromaDB, meaning it requires no API keys, cloud services, or external dependencies once installed. MemPalace emphasizes fidelity over compression, preserving full conversational history to maintain reasoning, nuance, and decision-making context that is typically lost in other systems. -
7
Audiogen Codec
48khz stereo neural audio codec for general audio
AGC (Audiogen Codec) is a convolutional autoencoder based on the DAC architecture, which holds SOTA. We found that training with EMA and adding a perceptual loss term with CLAP features improved performance. These codecs, being low compression, outperform Meta's EnCodec and DAC on general audio as validated from internal blind ELO games. We trained (relatively) very low compression codecs in the pursuit of solving a core issue regarding general music and audio generation, low acoustic quality, and audible artifacts, which hinder industry use for these models. Our hope is to encourage researchers to build hierarchical generative audio models that can efficiently use high sequence length representations without sacrificing semantic abilities. -
8
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
KVCache-Factory is an open-source research framework designed to explore and implement unified key-value cache compression techniques for autoregressive transformer models. In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. ... -
9
TurboQuant+
Implementation of TurboQuant (ICLR 2026)
TurboQuant Plus is an extended and enhanced version of quantization tooling aimed at improving neural network efficiency through advanced compression and optimization strategies. It builds upon the concept of reducing model precision to accelerate inference while attempting to maintain or recover accuracy through refined techniques. The project explores additional enhancements such as improved calibration, adaptive quantization, and potentially hybrid precision approaches that combine multiple levels of compression. -
Securden Privileged Account ManagerDiscover and manage administrator, service, and web app passwords, keys, and identities. Automate management with approval workflows. Centrally control, audit, monitor, and record all access to critical IT assets.
-
10
FramePack
Lets make video diffusion practical
...It’s useful for diffusion and generative models that learn from sequential image datasets, as well as classical pipelines that batch many related frames. With a simple API and examples, it invites experimentation on tradeoffs between compression, fidelity, and speed. -
11
R-KV
Redundancy-aware KV Cache Compression for Reasoning Models
R-KV is an open-source research project that focuses on improving the efficiency of large language model inference through key-value cache compression techniques. Modern transformer models rely heavily on KV caches during autoregressive decoding, which store intermediate attention states to accelerate generation. However, these caches can consume large amounts of memory, especially in reasoning-oriented models with long context windows. R-KV introduces a method for compressing the KV cache during decoding, allowing models to maintain reasoning performance while reducing memory consumption and computational overhead. ... -
12
Claude-Mem
Claude Code plugin that automatically captures everything Claude does
Claude-Mem is a persistent memory compression system built specifically for Claude Code to preserve context across coding sessions. It automatically captures Claude’s tool usage, observations, and decisions, then compresses them into semantic memories that carry forward into future sessions. By enabling long-term continuity, Claude-Mem helps Claude “remember” project history, past fixes, and prior reasoning even after restarts or reconnects. -
13
LMDeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs
LMDeploy is a toolkit designed for compressing, deploying, and serving large language models (LLMs). It offers tools and workflows to optimize LLMs for production environments, ensuring efficient performance and scalability. LMDeploy supports various model architectures and provides deployment solutions across different platforms. -
14
Claw Compactor
14-stage Fusion Pipeline for LLM token compression
Claw Compactor is a utility designed to optimize and manage the context limitations inherent in AI agent systems, particularly those built on OpenClaw-like architectures. It addresses the challenge of finite context windows in language models by compressing or summarizing historical interactions while preserving essential information. The system works by transforming older conversation data into condensed representations that maintain continuity without exceeding token limits. This approach... -
15
AIMET
AIMET is a library that provides advanced quantization and compression
...QuIC has a mission to help migrate the ecosystem toward fixed-point inference. With this goal, QuIC presents the AI Model Efficiency Toolkit (AIMET) - a library that provides advanced quantization and compression techniques for trained neural network models. AIMET enables neural networks to run more efficiently on fixed-point AI hardware accelerators. Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. ... -
16
Intel Extension for Transformers
Build your chatbot within minutes on your favorite device
Intel Extension for Transformers is an innovative toolkit designed to accelerate Transformer-based models on Intel platforms, including CPUs and GPUs. It offers state-of-the-art compression techniques for Large Language Models (LLMs) and provides tools to build chatbots within minutes on various devices. The extension aims to optimize the performance of Transformer-based models, making them more efficient and accessible. -
17
Koog
Koog is the official Kotlin framework for building AI agents
...It features pure Kotlin implementation, seamless Model Control Protocol (MCP) integration for enhanced model management, vector embeddings for semantic search, and a flexible system for creating and extending tools that access external systems and APIs. Ready‑to‑use components address common AI engineering challenges, while intelligent history compression optimizes token usage and preserves context. A powerful streaming API enables real‑time response processing and parallel tool calls. Persistent memory allows agents to retain knowledge across sessions and between agents, and comprehensive tracing facilities provide detailed debugging and monitoring. -
18
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle
...It features a PPOCR series of high-quality pre-trained models, which includes: ultra lightweight ppocr_mobile series models, general ppocr_server series models, and ultra lightweight compression ppocr_mobile_slim series models. PaddleOCR is easy to install and easy to use on Windows, Linux, MacOS and other systems. -
19
WavTokenizer
SOTA discrete acoustic codec models with 40/75 tokens per second
...It is built to represent speech, music, and general audio with extremely low bitrate, making it ideal as a front-end for large audio language models like GPT-4o and similar architectures. The model uses a single-quantizer design together with temporal compression to achieve extreme compression without sacrificing reconstruction fidelity. Its architecture incorporates a broader vector-quantization space, extended contextual windows, and improved attention networks, combined with multi-scale discriminators and inverse Fourier transform blocks to enhance waveform reconstruction. Extensive experiments show that WavTokenizer matches or surpasses previous neural codecs across speech, music, and general audio on both objective metrics and subjective listening tests. -
20
DOLMA
Data and tools for generating and inspecting OLMo pre-training data
DOLMA (Data Optimization and Learning for Model Alignment) is a framework designed to manage large-scale datasets for training and fine-tuning language models efficiently. -
21
FlexLLMGen
Running large language models on a single GPU
...The system focuses on high-throughput generation workloads where large batches of text must be processed quickly, such as large-scale data extraction or document analysis tasks. Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on commodity hardware. The architecture distributes computation and memory usage across the GPU, CPU, and disk in order to maximize the number of tokens processed during inference. This design allows organizations to deploy powerful language models for high-volume tasks without the infrastructure costs typically associated with large-scale AI systems. ... -
22
WFGY 3.0
A tension reasoning engine over 131 S-class problems
WFGY is an experimental open-source reasoning framework designed to improve the reliability and interpretability of large language model outputs through structured reasoning layers. The project introduces a conceptual reasoning engine that analyzes complex problems by identifying semantic compression errors and residual assumptions within a system’s reasoning process. Its architecture treats reasoning failures as measurable signals that can be detected and analyzed rather than simply observed as incorrect answers. Different versions of the framework, including WFGY 1.0, 2.0, and 3.0, represent stages of development where early conceptual ideas evolved into more structured reasoning engines and diagnostic tools. ... -
23
Edgee
AI gateway with token compression for Claude Code, Codex, and more
Edgee is an edge-native execution platform designed to run AI-driven logic and data processing directly at the network edge, reducing latency and improving responsiveness for modern applications. It enables developers to deploy functions and workflows closer to users, allowing real-time processing without relying heavily on centralized cloud infrastructure. The platform is built to support event-driven architectures, where actions are triggered by incoming requests, user behavior, or... -
24
Deep Lake
Data Lake for Deep Learning. Build, manage, and query datasets
...Use one API to upload, download, and stream datasets to/from AWS S3/S3-compatible storage, GCP, Activeloop cloud, or local storage. Store images, audios and videos in their native compression. Deeplake automatically decompresses them to raw data only when needed, e.g., when training a model. Treat your cloud datasets as if they are a collection of NumPy arrays in your system's memory. Slice them, index them, or iterate through them. -
25
Image Crop Picker
iOS/Android image picker with support for camera, video, etc.
Image Crop Picker is an iOS/Android image picker with support for camera, video, configurable compression, multiple images and cropping. Module is creating tmp images which are going to be cleaned up automatically somewhere in the future. If you want to force cleanup, you can use clean to clean all tmp files, or cleanSingle(path) to clean single tmp file. Some of these types may not be available on all iOS versions.
