Search Results for "compression"
Sort By:
Showing 128 open source projects for "compression"
View related business solutions-
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.
-
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.
-
1
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. -
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
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). -
4
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. ... -
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.
-
5
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. -
6
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. -
7
pg_probackup
Backup and recovery manager for PostgreSQL
pg_probackup is an advanced backup and recovery tool for PostgreSQL developed by PostgresPro. It supports full, incremental, and differential backups with compression and encryption, and provides fine-grained control over backup and restore processes. It’s designed for enterprise-grade backup strategies in PostgreSQL environments. -
8
ai-notebooks
Some ipython notebooks implementing AI algorithms
...The examples are written primarily in Python and use frameworks including TensorFlow, PyTorch, Keras, JAX, and tinygrad. Projects explore problems such as MNIST learning, GANs, VAEs, model compression, and knowledge distillation. Other notebooks examine reinforcement learning through PPO, SAC, TD3, VPG, and MuZero experiments. Transformer, recurrent-network, counterfactual-regret, and normalizing-flow examples broaden the collection. The notebooks are designed to be read directly on GitHub, making the repository useful for studying algorithms through working code. -
9
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. ... -
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
smart_open
Utils for streaming large files (S3, HDFS, gzip, bz2...)
...Supported backends include Amazon S3, Google Cloud Storage, Azure Blob Storage, HDFS, WebHDFS, HTTP, HTTPS, SFTP, and local filesystems. Data can be read or written without first downloading an entire remote object to disk. Transparent compression and decompression are supported for multiple common formats. Standard operations such as context managers, iteration, and supported seek behavior remain available. Optional transport dependencies let installations include only the cloud or protocol integrations an application actually requires. -
11
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. -
12
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. -
13
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. -
14
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. -
15
Requests
A simple, yet elegant, HTTP library.
Requests is the de facto HTTP library for Python—simple, elegant, and human-friendly. It wraps urllib3 to provide intuitive methods for sending HTTP/1.1 requests, handling sessions, cookies, redirects, authentication, proxies, and more. -
16
PyInstaller
Freeze (package) Python programs into stand-alone executables
PyInstaller freezes (packages) Python applications into stand-alone executables, under Windows, GNU/Linux, Mac OS X, FreeBSD, Solaris and AIX. PyInstaller’s main advantages over similar tools are that PyInstaller works with Python 3.5 to 3.9, it builds smaller executables thanks to transparent compression, it is fully multi-platform, and use the OS support to load the dynamic libraries, thus ensuring full compatibility. The main goal of PyInstaller is to be compatible with 3rd-party packages out-of-the-box. This means that, with PyInstaller, all the required tricks to make external packages work are already integrated within PyInstaller itself so that there is no user intervention required. ... -
17
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. ... -
18
PyMySQL
MySQL client library for Python
PyMySQL is a 100% Python implementation of the MySQL client protocol, allowing Python applications to connect to MySQL and MariaDB databases without requiring binary extensions. It supports standard DB‑API 2.0 features, such as cursors, transactions, and parameterized queries. PyMySQL is versatile for web applications, scripts, and tools, offering compatibility with ORMs like SQLAlchemy and frameworks like Django. -
19
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. ... -
20
gallery-dl
Command-line program to download image galleries and collections
gallery-dl is a powerful command-line tool designed to download image galleries and collections from a wide range of image hosting and media websites. Built with Python, it works across multiple operating systems including Windows, Linux, and macOS. The program allows users to download images, manga chapters, or media collections by simply providing a supported website URL. It includes extensive configuration options that allow users to control download behavior, file naming, and directory... -
21
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... -
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
Mangum
AWS Lambda support for ASGI applications
...Event handlers for API Gateway HTTP and REST APIs, Application Load Balancer, Function URLs, and CloudFront Lambda@Edge. Compatibility with ASGI application frameworks, such as Starlette, FastAPI, Quart and Django. Support for binary media types and payload compression in API Gateway using GZip or Brotli. Works with existing deployment and configuration tools, including Serverless Framework and AWS SAM. The heart of Mangum is the adapter class. It is a configurable wrapper that allows any ASGI application (or framework) to run in an AWS Lambda deployment. The adapter accepts a number of keyword arguments to configure settings related to logging, HTTP responses, ASGI lifespan, and API Gateway configuration. -
24
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. -
25
AWS SDK for pandas
Easy integration with Athena, Glue, Redshift, Timestream, Neptune
...With a few lines of code, you can read from and write to Amazon S3 in Parquet/CSV/JSON/ORC, register tables in the AWS Glue Data Catalog, and query with Amazon Athena directly into pandas. The library abstracts efficient patterns like partitioning, compression, and vectorized I/O so you get performant data lake operations without hand-rolling boilerplate. It also supports Redshift, OpenSearch, and other services, enabling ETL tasks that blend SQL engines and Python transformations. Operational helpers handle IAM, sessions, and concurrency while exposing knobs for encryption, versioning, and catalog consistency. ...
