Search Results for "compression" - Page 2
Sort By:
Showing 128 open source projects for "compression"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
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.
-
1
Headroom
Compress tool outputs, logs, files, and RAG chunks
Headroom is a context optimization layer for LLM applications that compresses information before it reaches the model. It sits between an application and an LLM provider, intercepting requests and forwarding a shorter optimized prompt. The project is designed to reduce token usage while preserving the answer quality needed for agent workflows. It can compress tool outputs, logs, RAG chunks, files, and conversation history. Headroom can be used as a transparent proxy, a Python function, a... -
2
SparseML
Libraries for applying sparsification recipes to neural networks
SparseML is an optimization toolkit for training and deploying deep learning models using sparsification techniques like pruning and quantization to improve efficiency. -
3
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. -
4
Django MarkdownX
Comprehensive Markdown plugin built for Django
Django MarkdownX is a comprehensive Markdown plugin built for Django, the renowned high-level Python web framework, with flexibility, extensibility, and ease-of-use at its core. -
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
turbovec
A vector index built on TurboQuant, written in Rust with Python
turbovec is a Rust-based vector index with Python bindings for fast similarity search. It is built around TurboQuant, a quantization approach designed to reduce vector storage while preserving useful distance information. The project targets workloads where embedding search needs to be compact, efficient, and practical to integrate into Python applications. It avoids a separate training phase for the quantizer, which can simplify setup compared with systems that require codebook learning.... -
6
Sherloq
An open source digital image forensic toolset
Sherloq is a research-oriented toolkit designed for digital image forensics, providing an integrated environment to experiment with algorithms for image analysis and tampering detection. Rather than functioning as an automated decision-making system, it serves as a companion tool for researchers, enthusiasts, and students who want to explore forensic techniques from scientific literature and workshops. The project emphasizes transparency and community collaboration, contrasting with... -
7
Upscale-A-Video
Temporal-Consistent Diffusion Model for Real-World Video
Upscale-A-Video is a diffusion-based video super-resolution project from the CVPR 2024 Highlight paper “Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution.” It upscales low-resolution videos while using text prompts to guide the enhancement process. The model is designed for real-world videos where compression artifacts, blur, aging, or generated-video defects can make ordinary upscaling less reliable. The repository includes inference code, example inputs, configuration structure, pretrained model instructions, and optional LLaVA-assisted prompt support. It includes example workflows for AIGC videos, old videos, movies, and animations. ... -
8
FastFlix
FastFlix is a free GUI for H.264, HEVC and AV1 hardware and software
...Its interface provides real-time feedback on encoding progress and estimated completion times. Overall, it serves as a user-friendly solution for high-quality video compression workflows. -
9
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. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
10
DeepSeek-OCR
Contexts Optical Compression
DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body... -
11
django-dbbackup
Management commands to help backup and restore your project database
django-dbbackup is a Django management command extension for backing up and restoring databases and media files. It supports multiple storage backends including local file systems, Amazon S3, and Dropbox. Ideal for automated backup strategies, it simplifies the integration of backup logic into Django projects. -
12
PGHoard
PostgreSQL® backup and restore service
pghoard is a PostgreSQL backup and restore tool that provides encrypted, compressed, and cloud-optimized backups. Developed by Aiven, it supports streaming WAL archiving and full base backups to various cloud storage backends. pghoard is designed for reliability and fast disaster recovery in cloud-native PostgreSQL deployments. -
13
Barman
Backup and Recovery Manager for PostgreSQL
Barman (Backup and Recovery Manager) is an enterprise-grade tool for managing backups and disaster recovery of PostgreSQL databases. It supports both full and incremental backups, Point-In-Time Recovery (PITR), and remote backup via SSH. Barman is widely used by DBAs to ensure secure, reliable, and consistent backups in production environments. -
14
Oil Motion
Create smooth, responsive interactive web animations
Oil Motion is an agent-agnostic skill for creating smooth interactive animations for websites and digital interfaces. Users describe the desired movement, available assets, and the interaction that should control it while the agent manages the production workflow. The system defines key states, generates continuous motion between them, reviews frames, removes artifacts, and prepares optimized assets. Animation progress can then be mapped to scrolling, mouse movement, dragging, touch input,... -
15
TurboQuant PyTorch
From-scratch PyTorch implementation of Google's TurboQuant
TurboQuant PyTorch is a specialized deep learning optimization framework designed to accelerate neural network inference and training through advanced quantization techniques within the PyTorch ecosystem. The project focuses on reducing the computational and memory footprint of models by converting floating-point representations into lower-precision formats while preserving performance. It provides tools for experimenting with different quantization strategies, enabling developers to balance... -
16
Responder
A familiar HTTP Service Framework for Python
...This gets you a ASGI app, with a production static files server (WhiteNoise) pre-installed, jinja2 templating (without additional imports), and a production web server based on uvloop, serving up requests with gzip compression automatically. A pleasant API, with a single import statement. Class-based views without inheritance. ASGI framework, the future of Python web services. WebSocket support! The ability to mount any ASGI / WSGI app at a subroute. f-string syntax route declaration. Mutable response object passed into each view. No need to return anything. ... -
17
PaddleX
PaddlePaddle End-to-End Development Toolkit
PaddleX is a deep learning full-process development tool based on the core framework, development kit, and tool components of Paddle. It has three characteristics opening up the whole process, integrating industrial practice, and being easy to use and integrate. Image classification and labeling is the most basic and simplest labeling task. Users only need to put pictures belonging to the same category in the same folder. When the model is trained, we need to divide the training set, the... -
18
FFmpeg Quality Metrics
Calculate quality metrics with FFmpeg (SSIM, PSNR, VMAF, VIF)
...Designed for cross-platform use, it integrates seamlessly into automated workflows and supports JSON or CSV output formats for further analysis. This makes it particularly valuable for engineers working on video compression and streaming systems. -
19
VidGear
A High-performance cross-platform Video Processing Python framework
VidGear is a high-performance Python framework that provides a unified and extensible solution for building real-time video processing applications. It acts as an abstraction layer over powerful multimedia libraries such as OpenCV, FFmpeg, and ZeroMQ, simplifying complex workflows into concise and efficient APIs. The framework is built around modular components called “gears,” each responsible for tasks such as video capture, streaming, encoding, and network transmission. It supports... -
20
NVIDIA Model Optimizer
A unified library of SOTA model optimization techniques
Model Optimizer is a unified library that provides state-of-the-art techniques for compressing and optimizing deep learning models to improve inference efficiency and deployment performance. It brings together multiple optimization strategies such as quantization, pruning, distillation, and speculative decoding into a single cohesive framework. The library is designed to reduce model size and computational requirements while maintaining accuracy, making it particularly valuable for deploying... -
21
LangChain Open Deep Research
Fully open source deep research agent
Open Deep Research is a configurable, fully open-source agent for producing detailed research reports from complex questions. It separates work across models used for summarization, active research, information compression, and final report generation. Users can select from multiple language model providers as long as the chosen models support tool calling and structured outputs. Search can be powered by several APIs, native provider search, or external tools connected through MCP. The agent runs on LangGraph and can be explored locally through LangGraph Studio, an API, and generated API documentation. ... -
22
LLM-Pruner
On the Structural Pruning of Large Language Models
LLM-Pruner is an open-source framework designed to compress large language models through structured pruning techniques while maintaining their general capabilities. Large language models often require enormous computational resources, making them expensive to deploy and inefficient for many practical applications. LLM-Pruner addresses this issue by identifying and removing non-essential components within transformer architectures, such as redundant attention heads or feed-forward... -
23
Torch Pruning
DepGraph: Towards Any Structural Pruning
...Torch-Pruning physically removes parameters rather than masking them, which results in smaller and faster models during both training and inference. The toolkit supports a wide variety of architectures used in computer vision and large language models, making it a flexible solution for model compression tasks. -
24
Advanced RAG Techniques
Advanced techniques for RAG systems
Advanced RAG Techniques is a comprehensive collection of tutorials and implementations focused on advanced Retrieval-Augmented Generation (RAG) systems. It is designed to help practitioners move beyond basic RAG setups and explore techniques that improve retrieval quality, context construction, and answer robustness. The repository organizes techniques into categories such as foundational RAG, query enhancement, context enrichment, and advanced retrieval, making it easier to navigate... -
25
DLRM
An implementation of a deep learning recommendation model (DLRM)
...The implementation is optimized for performance at scale, supporting multi-GPU and multi-node execution, quantization, embedding partitioning, and pipelined I/O to feed huge embeddings efficiently. It includes data loaders for standard benchmarks (like Criteo), training scripts, evaluation tools, and capabilities like mixed precision, gradient compression, and memory fusion to maximize throughput.
