Search Results for "parallel language"
Sort By:
Showing 55 open source projects for "parallel language"
View related business solutions-
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.
-
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
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. ... -
2
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. -
3
MathCode
A Frontier Mathematical Coding Agent
MathCode is a terminal-based AI coding assistant focused on mathematical formalization and theorem proving. It is designed to transform plain-language mathematical reasoning into verified Lean 4 code and formal proofs. The project combines AI agents with Lean Language Server Protocol integration, allowing it to inspect compiler feedback, search for lemmas, and iteratively repair failed proof attempts. It supports an agentic proving workflow where the system behaves more like an interactive... -
4
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. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
5
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. -
6
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... -
7
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... -
8
Triton
Development repository for the Triton language and compiler
Triton is a programming language and compiler framework specifically designed for writing highly efficient custom deep learning operations, particularly for GPUs. It aims to bridge the gap between low-level GPU programming, such as CUDA, and higher-level abstractions by providing a more productive and flexible environment for developers. Triton enables users to write optimized kernels for machine learning workloads while maintaining readability and control over performance-critical aspects like memory access patterns and parallel execution. ... -
9
Stanza
Stanford NLP Python library for many human languages
...Starting from raw text to syntactic analysis and entity recognition, Stanza brings state-of-the-art NLP models to languages of your choosing. Stanza is a Python natural language analysis package. It contains tools, which can be used in a pipeline, to convert a string containing human language text into lists of sentences and words, to generate base forms of those words, their parts of speech and morphological features, to give a syntactic structure dependency parse, and to recognize named entities. The toolkit is designed to be parallel among more than 70 languages, using the Universal Dependencies formalism. ... -
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.
-
10
MSA: Memory Sparse Attention
Trainable latent-memory framework for 100M-token contexts
...Its Memory Parallel engine distributes scoring and transfers only selected memory back to the accelerator. Memory Interleave alternates retrieval, context expansion, and generation to improve multi-hop reasoning across distant segments. The project reports experiments extending from 16K to 100M tokens, including inference on two A800 GPUs. -
11
jlens
Companion code for the global workspace interpretability paper
Jacobian Lens is Anthropic’s reference implementation for examining what a language model’s internal activations are inclined to produce as text. It transports residual-stream vectors from selected layers and positions into the final-layer basis using an averaged input-output Jacobian. The transformed vectors are decoded through the model’s own unembedding into ranked vocabulary predictions. The package can fit new lenses, load saved ones, apply them to prompts, and merge results from parallel fitting jobs. ... -
12
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
MiniMax-01 is the official repository for two flagship models: MiniMax-Text-01, a long-context language model, and MiniMax-VL-01, a vision-language model built on top of it. MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel strategies such as LASP+, varlen ring attention, and Expert Tensor Parallelism, enabling a training context of 1 million tokens and up to 4 million tokens at inference. ... -
13
Xtuner
A Next-Generation Training Engine Built for Ultra-Large MoE Models
Xtuner is a large-scale training engine designed for efficient training and fine-tuning of modern large language models, particularly mixture-of-experts architectures. The framework focuses on enabling scalable training for extremely large models while maintaining efficiency across distributed computing environments. Unlike traditional 3D parallel training strategies, XTuner introduces optimized parallelism techniques that simplify scaling and reduce system complexity when training massive models. ... -
14
Colossal-AI
Making large AI models cheaper, faster and more accessible
...However, distributed training, especially model parallelism, often requires domain expertise in computer systems and architecture. It remains a challenge for AI researchers to implement complex distributed training solutions for their models. Colossal-AI provides a collection of parallel components for you. We aim to support you to write your distributed deep learning models just like how you write your model on your laptop. -
15
Local Deep Research
95% on SimpleQA (e.g. Qwen3.6-27B on a 3090)
Local Deep Research is an open-source AI-powered research assistant designed to perform deep, iterative investigations by combining large language models with multi-source search capabilities. It runs locally, giving users full control over their data, privacy, and infrastructure while supporting both local and cloud-based LLMs. The system breaks down complex queries into smaller steps, performs parallel searches across web and academic sources, and generates structured, citation-backed reports. ... -
16
Droidrun
Powerful framework for controlling Android and iOS devices
Droidrun is a native mobile agent platform that gives users natural-language control over real Android devices to automate any mobile app workflow, from logins and bookings to purchases and data extraction, including access to mobile-only content behind app logins, rate limits, or platform restrictions. Its cloud offering lets users spin up agents in seconds with preinstalled apps, run tasks in parallel across multiple devices, and compose complex, multi-step conditional workflows using conversational commands; recorded workflows can be auto-replayed at high speed. ... -
17
ERNIE
The official repository for ERNIE 4.5 and ERNIEKit
...The project also emphasizes optimization techniques for large-scale training, including mixed-precision and hybrid-parallel strategies that are commonly needed for multi-node GPU clusters. In addition to training, it includes guidance and example materials intended to help developers adopt ERNIE models for real product scenarios rather than only research demonstrations. -
18
Atropos
Language Model Reinforcement Learning Environments frameworks
...It provides foundational tooling for asynchronous RL loops where environment services communicate with trainers and inference engines, enabling complex workflow orchestration in distributed and parallel setups. This framework facilitates experimentation with RLHF (Reinforcement Learning from Human Feedback), RLAIF, or multi-turn training approaches by abstracting environment logic, scoring, and logging into reusable components. -
19
video-use
Edit videos with Claude Code
Video Use is an open-source AI-powered video editing tool that allows users to transform raw footage into polished videos using natural language commands. Designed to work with Claude Code, it automates the entire editing process—from cutting clips to rendering the final output—without requiring manual timelines or complex software interfaces. The system intelligently analyzes audio transcripts and visual cues to make precise, context-aware editing decisions. It supports a wide range of... -
20
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. -
21
LangExtract
A Python library for extracting structured information
...LangExtract supports a wide range of models, including Google Gemini, OpenAI GPT, and local LLMs via Ollama, making it adaptable to different deployment environments and compliance needs. The system excels at handling long documents using optimized chunking, multi-pass extraction, and parallel processing to ensure both high recall and structured consistency. -
22
DeepEval is a simple-to-use, open-source LLM evaluation framework, for evaluating and testing large-language model systems. It is similar to Pytest but specialized for unit testing LLM outputs. DeepEval incorporates the latest research to evaluate LLM outputs based on metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., which uses LLMs and various other NLP models that run locally on your machine for evaluation. Whether your application is implemented via RAG or fine-tuning,...
-
23
BeeAI Framework
Build production-ready AI agents in both Python and Typescript
...The framework supports both Python and TypeScript with full feature parity, making it accessible to a wide range of developers and teams. It includes a unified backend layer that connects seamlessly to multiple large language model providers, allowing flexible deployment across different AI infrastructures without vendor lock-in. BeeAI also provides orchestration tools for designing dynamic workflows, enabling multiple agents to coordinate tasks through structured execution flows, retries, and parallel processing. -
24
fairseq2
FAIR Sequence Modeling Toolkit 2
...It supports multi-GPU and multi-node distributed training using DDP, FSDP, and tensor parallelism, capable of scaling up to 70B+ parameter models. The framework integrates seamlessly with PyTorch 2.x features such as torch.compile, Fully Sharded Data Parallel (FSDP), and modern configuration management. -
25
SCons
A software construction tool
SCons is a software construction tool that is a superior alternative to the classic "Make" build tool that we all know and love. SCons is implemented as a Python script and set of modules, and SCons "configuration files" are actually executed as Python scripts. This gives SCons many powerful capabilities not found in other software build tools. We make SCons available in three distinct packages, for different purposes. - The scons package is the basic package to install SCons. You...
