Search Results for "mixture"

...The library is designed to work cleanly and simply, avoiding overly templated or heavily abstracted code, while still delivering performance that rivals expert-tuned libraries. It supports both standard and “grouped” GEMMs, which is useful for architectures like Mixture of Experts (MoE) that require segmented matrix multiplications. One distinguishing aspect is that DeepGEMM compiles its kernels at runtime (via a lightweight Just-In-Time (JIT) module), so users don’t need to precompile CUDA kernels before installation. Despite its lean design, it includes scaling strategies (fine-grained scaling) and optimizations inspired by cutting edge systems (drawing from ideas in CUTLASS, CuTe) but in a more streamlined form.

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.

Kaldi is an open source toolkit for speech recognition research. It provides a powerful framework for building state-of-the-art automatic speech recognition (ASR) systems, with support for deep neural networks, Gaussian mixture models, hidden Markov models, and other advanced techniques. The toolkit is widely used in both academia and industry due to its flexibility, extensibility, and strong community support. Kaldi is designed for researchers who need a highly customizable environment to experiment with new algorithms, as well as for practitioners who want robust, production-ready ASR pipelines. ...

...UCCL is designed to work with heterogeneous hardware environments, allowing GPUs from different vendors and network interfaces to communicate efficiently without vendor lock-in. The system also supports specialized workloads such as reinforcement learning weight transfers, key-value cache sharing, and expert parallelism for mixture-of-experts models. Its architecture emphasizes flexibility and extensibility so that developers can implement custom communication protocols tailored to specific machine learning workloads.

* Fast C++ library for linear algebra (matrix maths) and scientific computing * Easy to use functions and syntax, deliberately similar to Matlab / Octave * Uses template meta-programming techniques to increase efficiency * Provides user-friendly wrappers for OpenBLAS, Intel MKL, LAPACK, ATLAS, ARPACK, SuperLU and FFTW libraries * Useful for machine learning, pattern recognition, signal processing, bioinformatics, statistics, finance, etc. * Downloads:...

MLPACK is a C++ machine learning library with emphasis on scalability, speed, and ease-of-use. Its aim is to make machine learning possible for novice users by means of a simple, consistent API, while simultaneously exploiting C++ language features to provide maximum performance and flexibility for expert users. * More info + downloads: https://mlpack.org * Git repo: https://github.com/mlpack/mlpack

...As a DBMS, RAQUEL is to : 1. have an Open Architecture, enabling a variety of DBMS configurations of 'black box' code, each installation optimised for a certain kind of DB; 2. be a stack of core black boxes to provide general DBMS functionality, plus a range of plug-in black boxes to support different physical storage mechanisms & scalar data types; 3. employ code designed with a mixture of functional, OO & other methods so as to minimise internal DBMS state complexity. The 'Northumbria Website' (above RHS menu option) describes the vision, specification & design of the RAQUEL language & DBMS architecture.

An extremely scriptable high-performance game engine suitable for building large streaming games with realistic graphics/physics in a seamless mixture of environments with broad gameplay opportunities.

A small flexible library plugin to calculate mixture fraction from species fields in OpenFOAM.

...To infer the structure of community-level metabolic interactions, BiomeNet applies a mixed-membership modelling framework to enzyme abundance information. The basic idea is that the mixture components of the model (metabolic reactions, subnetworks, and networks) are shared across all groups (microbiome samples), but the mixture proportions vary from group to group. Through this framework, the model can capture nested structures within the data. BiomeNet is unique in modeling each metagenome sample as a mixture of complex metabolic systems (metabosystems).

de:Code is a 3rd-person top-down dungeon crawler. The world is procedurally generated using the file structure of the users hard drive. The game will use a mixture of different genres including steampunk, fantasy, mid-evil, and modern. The user will have to travel down 4 main paths each progressively harder than the last and each will have more than one genre conflicting inside. Each main path (connected by a central hub) will get harder as the user progresses down, finally reaching a unique boss at the end.

BigBang/Horizon is a proteomics data analysis pipeline with focus on the shotgun LC/MSMS workflow.

ENIGMA is a free game and application development toolkit, utilizing GCC and a series of parsers to convert a high level, script-like language based on Game Maker's GML, into C++. The toolkit employs a mixture of both C++ and GML, accepting either.

test *only* 1) nr3, Poisson distribution 2) mixture model

GMM-GMR is a light package of functions in C/C++ to compute Gaussian Mixture Model (GMM) and Gaussian Mixture Regression (GMR). It allows to encode any dataset in a GMM, and GMR can then be used to retrieve partial data by specifying the desired inputs.

kiki the nanobot is a 3-D puzzle game. It is basically a mixture of the games Sokoban and Kula-World.

A RTS game which will be a mixture of some classic games like Populous and Megalomaniacs.

LUPUS (LUPUS Universal Plattformindependent Update System) is a powerful tool for system-administrators. It's some kind of mixture of apt, dpkg, subversion, cfengine and qmake ;-)

This program developed into DYNAMO, the general event driven dynamics simulator. This is capable of simulating millions of particles and a huge range of complex dynamics. Please see the new website at http://www.marcusbannerman.co.uk/dynamo

This project aims at writing a threaded, object-oriented and scriptable game engine targetting the .NET platform, using a mixture of c# or managed c++ ports of famous c/c++ components such as OGRE, CEGUI, Newton, Lua, Python, Audiere, OpenAL, etc...

MechForce is the coolest shareware game on the Amiga (IMHO). It's a mixture of realtime and turn based strategy/tactic game based on BattleTech. This is an attempt to recreate this game with a lot of enhancements with the help of the Allegro library.

Computergame which uses the Irrlichtengine for graphics and the ODE-engine for physics. It's a racing-game, but you don't drive with cars - you fly with glider about 0.5-1 metre in the air. It's fast and fun. It's like a mixture of f-zero and a norma

Kolumns is inspired by Sega's Columns. The game is a mixture of Tetris and maybe Tic-Tac-Toe (the goal is consecutive blocks of the same color). Nice graphics. Easy & fun to play! The game runs on KDE 3.x for Linux or other Unix-like platforms. Do

A mixture of Zelda II with Dungeans and Dragons. Huge world to play.

A video game with a mixture of 2D, 3D graphics, but mostly 2D. Currently in the planning phase. Database oriented, with multiplayer gameplay intended. Also with an underlying translation framework for Hindi and Japanese.