Search Results for "sparse" - Page 2
Sort By:
Showing 180 open source projects for "sparse"
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.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
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. -
2
Ling-V2
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI
Ling-V2 is an open-source family of Mixture-of-Experts (MoE) large language models developed by the InclusionAI research organization with the goal of combining state-of-the-art performance, efficiency, and openness for next-generation AI applications. It introduces highly sparse architectures where only a fraction of the model’s parameters are activated per input token, enabling models like Ling-mini-2.0 to achieve reasoning and instruction-following capabilities on par with much larger dense models while remaining significantly more computationally efficient. Trained on more than 20 trillion tokens of high-quality data and enhanced through multi-stage supervised fine-tuning and reinforcement learning, Ling-V2’s models demonstrate strong general reasoning, mathematical problem-solving, coding understanding, and knowledge-intensive task performance. -
3
Step 3.5 Flash
Fast, Sharp & Reliable Agentic Intelligence
Step 3.5 Flash is a cutting-edge, open-source large language model developed by StepFun-AI that pushes the frontier of efficient reasoning and “agentic” intelligence in a way that makes powerful AI accessible beyond proprietary black boxes. Unlike dense models that activate all their parameters for every token, Step 3.5 Flash uses a sparse Mixture-of-Experts (MoE) architecture that selectively engages only about 11 billion of its roughly 196 billion total parameters per token, delivering high-quality reasoning and interaction at far lower compute cost and latency than traditional large models. Its design targets deep reasoning, long-context handling, coding, and real-time responsiveness, making it suitable for building autonomous agents, advanced assistants, and long-chain cognitive workflows without sacrificing performance. -
4
go-datastructures
A collection of useful, performant, and threadsafe Go datastructures
...Bitarray used to detect existence without having to resort to hashing with hashmaps. Requires entities have a uint64 unique identifier. Two implementations exist, regular and sparse. Sparse saves a great deal of space but insertions are O(log n). There are some useful functions on the BitArray interface to detect intersection between two bitarrays. This package also includes bitmaps of length 32 and 64 that provide increased speed and O(1) for all operations by storing the bitmaps in unsigned integers rather than arrays. -
Build Securely on Azure 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
BEIR
A Heterogeneous Benchmark for Information Retrieval
BEIR is a benchmark framework for evaluating information retrieval models across various datasets and tasks, including document ranking and question answering. -
6
The Operator Splitting QP Solver
The Operator Splitting QP Solver
OSQP uses a specialized ADMM-based first-order method with custom sparse linear algebra routines that exploit structure in problem data. The algorithm is absolutely division-free after the setup and it requires no assumptions on problem data (the problem only needs to be convex). It just works. OSQP has an easy interface to generate customized embeddable C code with no memory manager required. OSQP supports many interfaces including C/C++, Fortran, Matlab, Python, R, Julia, Rust. -
7
FastRAG
Efficient Retrieval Augmentation and Generation Framework
fastRAG is a research framework for efficient and optimized retrieval augmented generative pipelines, incorporating state-of-the-art LLMs and Information Retrieval. fastRAG is designed to empower researchers and developers with a comprehensive tool set for advancing retrieval augmented generation. -
8
Symbolics.jl
Symbolic programming for the next generation of numerical software
Symbolics.jl is a high-performance symbolic computation library for the Julia programming language. It enables users to define, manipulate, and analyze mathematical expressions symbolically, with strong support for symbolic differentiation, simplification, equation solving, and code generation. Designed for use in scientific computing, machine learning, and engineering, Symbolics.jl integrates smoothly with Julia’s numerical ecosystem, allowing symbolic expressions to be compiled and... -
9
DeepSparse
Sparsity-aware deep learning inference runtime for CPUs
A sparsity-aware enterprise inferencing system for AI models on CPUs. Maximize your CPU infrastructure with DeepSparse to run performant computer vision (CV), natural language processing (NLP), and large language models (LLMs). -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
10
MNE-Python
Magnetoencephalography (MEG) and Electroencephalography EEG in Python
Open-source Python package for exploring, visualizing, and analyzing human neurophysiological data. MNE-Python is an open-source Python package for exploring, visualizing, and analyzing human neurophysiological data such as MEG, EEG, sEEG, ECoG, and more. It includes modules for data input/output, preprocessing, visualization, source estimation, time-frequency analysis, connectivity analysis, machine learning, statistics, and more. -
11
Bevy
A refreshingly simple data-driven game engine built in Rust
...Bevy is still in the very early stages of development. APIs can and will change (now is the time to make suggestions!). Important features are missing. Documentation is sparse. Please don't build any serious projects in Bevy unless you are prepared to be broken by API changes constantly. Bevy relies heavily on improvements in the Rust language and compiler. As a result, the Minimum Supported Rust Version (MSRV) is "the latest stable release" of Rust. Built directly on top of Bevy's ECS, Renderer, and Scene plugins. -
12
Dgraph
The Only Native GraphQL Database With A Graph Backend
...It provides consistent replication, automatic data movement for shard balancing, distributed ACID transactions, as well as native support for full text search, regular expressions and geo search. If you have over 10 SQL tables interconnected via foreign keys, or sparse data that don’t fit neatly into SQL tables; or if you just want a simple and flexible schema, and prioritize speed and performance at scale, Dgraph is the best choice for you. It’s fully equipped with everything you need and more. -
13
QuantumClifford.jl
Clifford circuits, graph states, and other quantum Stabilizer tools
A Julia package for working with quantum stabilizer states and Clifford circuits that act on them. Graphs states are also supported. The package is already very fast for the majority of common operations, but there are still many low-hanging fruits performance-wise. See the detailed suggested readings & references page for background on the various algorithms. -
14
HunyuanImage-3.0
A Powerful Native Multimodal Model for Image Generation
HunyuanImage-3.0 is a powerful, native multimodal text-to-image generation model released by Tencent’s Hunyuan team. It unifies multimodal understanding and generation in a single autoregressive framework, combining text and image modalities seamlessly rather than relying on separate image-only diffusion components. It uses a Mixture-of-Experts (MoE) architecture with many expert subnetworks to scale efficiently, deploying only a subset of experts per token, which allows large parameter... -
15
FiniteDifferences.jl
High accuracy derivatives, estimated via numerical finite differences
FiniteDifferences.jl estimates derivatives with finite differences. See also the Python package FDM. FiniteDiff.jl and FiniteDifferences.jl are similar libraries: both calculate approximate derivatives numerically. You should definitely use one or the other, rather than the legacy Calculus.jl finite differencing, or reimplementing it yourself. At some point in the future, they might merge, or one might depend on the other. -
16
TensorRT
C++ library for high performance inference on NVIDIA GPUs
...TensorRT is built on CUDA®, NVIDIA’s parallel programming model, and enables you to optimize inference leveraging libraries, development tools, and technologies in CUDA-X™ for artificial intelligence, autonomous machines, high-performance computing, and graphics. With new NVIDIA Ampere Architecture GPUs, TensorRT also leverages sparse tensor cores providing an additional performance boost. -
17
EnTT
A fast and reliable entity component system (ECS) and much more
...Statically generated integer identifiers for types (assigned either at compile-time or at runtime). A constexpr utility for human readable resource names. An incredibly fast entity-component system based on sparse sets, with its own pay for what you use policy to adjust performance and memory usage according to the users' requirements. Offers a minimal configuration system built using the monostate pattern. -
18
MonoTorrent
The repository for MonoTorrent, a bittorrent library for .NET
This is a list of all the BEPs which have been implemented in MonoTorrent. A full list of all available BEPs can be seen. Prioritise specific files. Selective file downloading (including the ability to not download specific files). Rarest first piece picking (takes priorisation into account). End-game mode to boost the last 1-2% of the download. Sequential downloading (for media files). Per-torrent download/upload rate limiting. Overall download/upload rate limiting. In memory cache to... -
19
Transformer Debugger
Tool for exploring and debugging transformer model behaviors
Transformer Debugger (TDB) is a research tool developed by OpenAI’s Superalignment team to investigate and interpret the behaviors of small language models. It combines automated interpretability methods with sparse autoencoders, enabling researchers to analyze how specific neurons, attention heads, and latent features contribute to a model’s outputs. TDB allows users to intervene directly in the forward pass of a model and observe how such interventions change predictions, making it possible to answer questions like why a token was selected or why an attention head focused on a certain input. ... -
20
Vowpal Wabbit
Machine learning system which pushes the frontier of machine learning
...There can even be multiple sets of free-form text in different namespaces. Similar to the few other online algorithm implementations out there. There are several optimization algorithms available with the baseline being sparse gradient descent (GD) on a loss function. -
21
DeepSeed
Deep learning optimization library making distributed training easy
...With just a single GPU, ZeRO-Offload of DeepSpeed can train models with over 10B parameters, 10x bigger than the state of arts, democratizing multi-billion-parameter model training such that many deep learning scientists can explore bigger and better models. Sparse attention of DeepSpeed powers an order-of-magnitude longer input sequence and obtains up to 6x faster execution comparing with dense transformers. -
22
TurboDiffusion
100–200× Acceleration for Video Diffusion Models
TurboDiffusion is an advanced open-source framework designed to dramatically accelerate video diffusion model generation, aiming for performance improvements on the order of 100–200× compared with traditional implementations while retaining high output quality. It achieves this by combining a suite of algorithmic and engineering optimizations, including attention acceleration techniques, efficient step distillation methods, and quantization strategies that reduce computational overhead. The... -
23
Sparse Indoor Camera Datasets
Positioning indoor cameras without overlapping in large scenarios.
...This system, which improves upon existing techniques, includes a comprehensive optimization process and has been validated with specially created datasets. Code project: https://sourceforge.net/projects/sparse-indoor-camera-poses/ -
24
Sparse Indoor Camera Poses
Positioning indoor cameras without overlapping in large scenarios.
This paper presents a novel method for positioning fixed indoor cameras with and without overlapping views, using fiducial markers and a mobile camera. This system, which improves upon existing techniques, includes a comprehensive optimization process and has been validated with specially created datasets. -
25
Ling
Ling is a MoE LLM provided and open-sourced by InclusionAI
Ling is a Mixture-of-Experts (MoE) large language model (LLM) provided and open-sourced by inclusionAI. The project offers different sizes (Ling-lite, Ling-plus) and emphasizes flexibility and efficiency: being able to scale, adapt expert activation, and perform across a range of natural language/reasoning tasks. Example scripts, inference pipelines, and documentation. The codebase includes inference, examples, models, documentation, and model download infrastructure. As more developers and...
