Search Results for "compression"
Sort By:
22 projects for "compression" with 2 filters applied:
-
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.
-
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
1
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. -
2
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. ... -
3
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. -
4
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. ... -
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.
-
5
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. -
6
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. -
7
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... -
8
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. ... -
9
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. ... -
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
10
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... -
11
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... -
12
Lossless Claw
LCM (Lossless Context Management) plugin for OpenClaw
...The system stores every interaction in a persistent database and incrementally summarizes older content into a hierarchical directed acyclic graph, allowing efficient compression without discarding information. This structure enables agents to dynamically reconstruct detailed context by expanding summaries when needed, effectively simulating perfect long-term memory. -
13
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. -
14
OAGI Python SDK
Python SDK for the Computer Use model Lux, developed by OpenAGI
OAGI Python SDK is a Python client library for the Lux computer-use model that turns Lux into a programmable automation layer for operating human-facing software via vision and actions. It exposes the OAGI API in an ergonomic way, letting you trigger Lux in three main modes: Tasker for precise scripted sequences, Actor for fast one-shot tasks, and Thinker for open-ended, multi-step objectives. The SDK is designed around “computer use” as a paradigm, where the AI actually navigates... -
15
Advanced + Agentic RAG Cookbooks
Advanced RAG cookbooks for building accurate LLM applications
...Athina AI’s RAG Cookbooks covers the full RAG pipeline, including indexing, retrieval, augmentation, and generation, while also addressing evaluation to measure accuracy and relevance. It includes multiple approaches such as hybrid search, contextual compression, and agent-based retrieval strategies, allowing users to experiment and compare methods. It is designed to reduce development time by offering practical examples and references to research papers, making it useful for both learning and production use. Overall, it serves as a hands-on resource for improving LLM outputs using external data sources. -
16
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... -
17
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... -
18
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. -
19
ERNIE
The official repository for ERNIE 4.5 and ERNIEKit
ERNIE is an open-source large-model toolkit and model family from the PaddlePaddle ecosystem that focuses on training, fine-tuning, compression, and practical application of ERNIE large language models. The repository positions ERNIEKit as an industrial-grade development toolkit, emphasizing end-to-end workflows that span high-performance pre-training, supervised fine-tuning, and alignment. It supports both full-parameter training and parameter-efficient approaches so teams can choose between maximum quality and lower-cost adaptation depending on their constraints. ... -
20
ADAMS
ADAMS is a workflow engine for building complex knowledge workflows.
ADAMS is a flexible workflow engine aimed at quickly building and maintaining data-driven, reactive workflows, easily integrated into business processes. Instead of placing operators on a canvas and manually connecting them, a tree structure and flow control operators determine how data is processed (sequentially/parallel). This allows rapid development and easy maintenance of large workflows, with hundreds or thousands of operators. Operators include machine learning (WEKA, MOA, MEKA)... -
21
Bolt ML
10x faster matrix and vector operations
Bolt is an open-source research project focused on accelerating machine learning and data mining workloads through efficient vector compression and approximate computation techniques. The core idea behind Bolt is to compress large collections of dense numeric vectors and perform mathematical operations directly on the compressed representations instead of decompressing them first. This approach significantly reduces both memory usage and computational overhead when working with high-dimensional data commonly used in machine learning systems. ... -
22
Immutable Sparse Wave Trees (WaveTree)
Realtime bigdata tool for bit strings up to 2^63 based on AVL forest
...Example: instead of building a class to hold a header and then data, represent all of that as Bits, subranges of them, and ints for sizes of its parts. Expansion ability for other kinds of compression, since Bits is a Java interface. Main functions on bits are substring, concat, number of 0 or 1 bits, and number of bits (size). All those operations can be done millions of times per second regardless of size because the AVL forest reuses existing branches recursively. Theres a scalar (originally for copy/pasting subranges of sounds) and a bit Java package. ...
- Previous
- You're on page 1
- Next
