Search Results for "parallel"
Sort By:
Showing 94 open source projects for "parallel"
View related business solutions-
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.
-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
Brax
Massively parallel rigidbody physics simulation
Brax is a fast and fully differentiable physics engine for large-scale rigid body simulations, built on JAX. It is designed for research in reinforcement learning and robotics, enabling efficient simulations and gradient-based optimization. -
2
Claude Ads
Comprehensive paid advertising audit & optimization skill
...The system generates structured reports, identifies inefficiencies, and suggests optimization strategies based on industry benchmarks. It supports platforms like Google Ads, Meta Ads, TikTok, LinkedIn, and more, offering a unified analysis workflow. The architecture uses parallel subagents to speed up audits and includes financial modeling and A/B testing guidance. It runs locally, ensuring privacy and control over sensitive advertising data. The project is aimed at replacing manual audit workflows with fast, automated, and repeatable analysis. -
3
mosaicml composer
Supercharge Your Model Training
...The framework is intended for modern workloads that may span anything from a single GPU to very large distributed training environments, which makes it suitable for both experimentation and production-scale development. It includes built-in support for distributed training strategies such as Fully Sharded Data Parallelism and standard Distributed Data Parallel execution, helping teams scale models without having to assemble as much infrastructure by hand. -
4
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
...The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU memory usage / improve efficiency. Parallel inference code to speed up sampling, utilities and tests included. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
vLLM
A high-throughput and memory-efficient inference and serving engine
vLLM is a fast and easy-to-use library for LLM inference and serving. High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more. -
6
Eigent
The Open Source Cowork Desktop to Unlock Your Exceptional Productivity
Eigent is an open-source cowork desktop application designed to help you build, manage, and deploy a custom AI workforce. It enables multiple specialized AI agents to collaborate in parallel, turning complex workflows into automated, end-to-end tasks. Built on the CAMEL-AI multi-agent framework, Eigent emphasizes productivity, flexibility, and transparent system design. You can run Eigent fully locally for maximum privacy and data control, or choose a cloud-connected experience for quick access. The platform supports a wide range of AI models and integrates powerful tools through the Model Context Protocol (MCP). ... -
7
Loki Mode
Multi-agent autonomous startup system for Claude Code
...It orchestrates dozens of agent types across swarms that handle designated roles — such as architecture, coding, QA, deployment, and business workflows — running in parallel to cover both engineering and operational tasks without continuous human intervention. By supporting multiple AI providers (like Claude Code, OpenAI Codex CLI, and Google Gemini CLI), loki-mode dynamically selects and spawns only the needed agents for a given project, optimizing computational resources and task throughput. Its Reason-Act-Reflect-Verify (RARV) cycle with self-verification loops emphasizes quality and resilience, automating end-to-end development lifecycles. -
8
DFlash
Block Diffusion for Ultra-Fast Speculative Decoding
DFlash is an open-source framework for ultra-fast speculative decoding using a lightweight block diffusion model to draft text in parallel with a target large language model, dramatically improving inference speed without sacrificing generation quality. It acts as a “drafter” that proposes likely continuations which the main model then verifies, enabling significant throughput gains compared to traditional autoregressive decoding methods that generate token by token. -
9
HunyuanVideo-I2V
A Customizable Image-to-Video Model based on HunyuanVideo
...It extends video generation so that given a static reference image plus an optional prompt, it generates a video sequence that preserves the reference image’s identity (especially in the first frame) and allows stylized effects via LoRA adapters. The repository includes pretrained weights, inference and sampling scripts, training code for LoRA effects, and support for parallel inference via xDiT. Resolution, video length, stability mode, flow shift, seed, CPU offload etc. Parallel inference support using xDiT for multi-GPU speedups. LoRA training / fine-tuning support to add special effects or customize generation. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
10
Swarms
Enterprise multi-agent orchestration framework for scalable AI apps
Swarms is an enterprise-grade multi-agent orchestration framework designed to help developers build, manage, and scale collaborative AI systems composed of multiple agents. It provides a structured infrastructure for coordinating agents in hierarchical, parallel, or sequential workflows, enabling complex task execution across distributed components. It emphasizes production readiness, offering modular architecture, high availability, and observability features suitable for large-scale deployments. It supports integration with multiple model providers and existing ecosystems, allowing developers to combine different AI tools and frameworks within a unified system. ... -
11
Apodex FrontierAgent
FrontierAgent, our agent framework, open-sourced alongside it
...Its ReAct workflow provides a stateful agent that can research, read files, execute commands, and create deliverables inside a task-scoped sandbox. Agent Team mode adds a coordinator that divides work among parallel sub-agents and synthesizes their results. A live task board tracks pending, active, completed, blocked, and canceled work. Users can provide new instructions while an agent is running without discarding the active session. The same modular workflow engine also powers benchmark evaluations and can connect to OpenAI-compatible model endpoints. -
12
Inspect Petri
An alignment auditing agent capable of exploring alignment hypothesis
...The system supports major model APIs and comes with starter seeds and judge dimensions, enabling minutes-to-insight workflows for questions like reward hacking, self-preservation, or eval awareness. Petri is designed for parallel exploration: it spins many audits in flight, aggregates findings, and highlights transcripts that deserve human review. -
13
Implicit
Fast Python collaborative filtering for implicit feedback datasets
This project provides fast Python implementations of several different popular recommendation algorithms for implicit feedback datasets. All models have multi-threaded training routines, using Cython and OpenMP to fit the models in parallel among all available CPU cores. In addition, the ALS and BPR models both have custom CUDA kernels - enabling fitting on compatible GPU’s. This library also supports using approximate nearest neighbour libraries such as Annoy, NMSLIB and Faiss for speeding up making recommendations. -
14
Flow-Next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex
Flow-Next is a workflow orchestration tool designed to manage complex processes by structuring tasks into organized and repeatable pipelines. It focuses on improving productivity by allowing users to define workflows that can be executed step by step or in parallel. The system emphasizes modularity, enabling tasks to be broken down into smaller components that can be reused across different workflows. It supports integration with various tools and services, making it adaptable to different environments. The project is designed to handle both simple and complex workflows, providing flexibility for a wide range of use cases. ... -
15
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
BigMac is an open-source toolkit for pipeline-parallel training of multimodal large language models. It preserves optimized language-model pipeline schedules while placing encoder and generator work around them. This design reduces activation memory without bringing back cross-module pipeline bubbles. Its scheduler creates global operator plans, while its executor runs those plans through a shared schedule abstraction. -
16
Open SWE
Open source async coding agent that plans, codes, and opens PRs
...Built with LangGraph, it can understand a codebase, generate a structured plan, and execute code changes from start to finish without constant human intervention. It operates in a cloud-based environment where tasks are processed asynchronously, allowing multiple coding jobs to run in parallel in isolated sandboxes. It integrates directly with development workflows by responding to triggers from tools like GitHub, enabling users to initiate tasks through issues or comments. Open SWE is capable of creating commits and automatically opening pull requests once implementation is complete, effectively closing the loop on development tasks. ... -
17
Megatron
Ongoing research training transformer models at scale
Megatron is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA. This repository is for ongoing research on training large transformer language models at scale. We developed efficient, model-parallel (tensor, sequence, and pipeline), and multi-node pre-training of transformer based models such as GPT, BERT, and T5 using mixed precision. Megatron is also used in NeMo Megatron, a framework to help enterprises overcome the challenges of building and training sophisticated natural language processing models with billions and trillions of parameters. ... -
18
magentic
Seamlessly integrate LLMs as Python functions
Easily integrate Large Language Models into your Python code. Simply use the @prompt and @chatprompt decorators to create functions that return structured output from the LLM. Mix LLM queries and function calling with regular Python code to create complex logic. -
19
MiroFish
A Simple and Universal Swarm Intelligence Engine
MiroFish is a next-generation artificial intelligence prediction engine that leverages multi-agent technology and swarm-intelligence simulation to model, simulate, and forecast complex real-world scenarios. The system extracts “seed” information from sources such as breaking news, policy documents, and market signals to construct a high-fidelity digital parallel world populated by thousands of virtual agents with independent memory and behavior rules. Users can inject variables or conditions into this simulated environment from a “god’s eye view,” enabling iterative prediction of future trends under different assumptions, which can be useful for decision support, scenario planning, or creative exploration. ... -
20
OpenSRE
Build your own AI SRE agents. The open source toolkit for the AI era
...When an alert is triggered, the system autonomously analyzes correlated signals, identifies anomalies, and generates structured investigation reports with probable causes and recommended actions. Its multi-agent architecture allows parallel reasoning across systems, mimicking how experienced SRE teams debug complex issues. The platform also incorporates memory and knowledge graph capabilities to learn from past incidents and improve future investigations. It is designed to run locally within an organization’s infrastructure, ensuring data privacy and compliance. -
21
MCP Agent Mail
Asynchronous coordination layer for AI coding agents
...It gives each agent a persistent identity, inbox, outbox, searchable history, and threaded Markdown conversations. Agents can send decisions, status updates, images, and attachments without relying on a human to relay context between parallel sessions. Advisory file reservations let an agent declare intended edits to files or patterns, reducing accidental overlap without enforcing rigid locks. Git stores human-auditable communication artifacts, while SQLite supports indexing, search, and operational queries. The HTTP-only FastMCP server works with clients such as Claude Code, Codex, Gemini CLI, and other MCP-compatible tools. ... -
22
FuXi
FuXi is a fast, self-contained AI coding agent
...It supports cost-aware routing and automatic failover across multiple LLM providers, including OpenAI-compatible services and other supported backends. More than 50 built-in tools cover file operations, shell access, search, diagnostics, Jupyter, browser use, background tasks, and parallel sub-agents. Sessions are persistent, extensible through MCP, hooks, skills, and plugins, and protected by command classification, permissions, and audit logging. -
23
VectorizedMultiAgentSimulator (VMAS)
VMAS is a vectorized differentiable simulator
VectorizedMultiAgentSimulator is a high-performance, vectorized simulator for multi-agent systems, focusing on large-scale agent interactions in shared environments. It is designed for research in multi-agent reinforcement learning, robotics, and autonomous systems where thousands of agents need to be simulated efficiently. -
24
DataChain
AI-data warehouse to enrich, transform and analyze unstructured data
Datachain enables multimodal API calls and local AI inferences to run in parallel over many samples as chained operations. The resulting datasets can be saved, versioned, and sent directly to PyTorch and TensorFlow for training. Datachain can persist features of Python objects returned by AI models, and enables vectorized analytical operations over them. The typical use cases are data curation, LLM analytics and validation, image segmentation, pose detection, and GenAI alignment. ... -
25
Parallax
Parallax is a distributed model serving framework
Parallax is a decentralized inference framework designed to run large language models across distributed computing resources. Instead of relying on centralized GPU clusters in data centers, the system allows multiple heterogeneous machines to collaborate in serving AI inference workloads. Parallax divides model layers across different nodes and dynamically coordinates them to form a complete inference pipeline. A two-stage scheduling architecture determines how model layers are allocated to...
