Search Results for "parallel language"
Sort By:
Showing 31 open source projects for "parallel language"
View related business solutions-
Your go-to FinOps platformUnlike reporting-only FinOps tools, FinOpsly unifies cloud (AWS, Azure, GCP), data (Snowflake, Databricks, BigQuery), and AI costs into a single system of action — enabling teams to plan spend before it happens, automate optimization safely, and prove value in weeks, not quarters.
-
Powerful Website Security | Continuous Web Threat PlatformReflectiz is a comprehensive web exposure management platform that helps organizations proactively identify, monitor, and mitigate security, privacy, and compliance risks across their online environments. Designed to address the growing complexity of modern websites, Reflectiz provides full visibility and control over first, third, and even fourth-party components, such as scripts, trackers, and open-source libraries that often evade traditional security tools.
-
1
LLMCompiler
An LLM Compiler for Parallel Function Calling
LLMCompiler is an open-source framework designed to optimize how large language models orchestrate multiple external tool or function calls during complex reasoning tasks. Traditional LLM agent systems typically execute tool calls sequentially, which can create latency, higher costs, and reduced reliability when solving multi-step problems. LLMCompiler addresses this limitation by applying principles from classical compilers to analyze a task and construct an execution plan that allows multiple functions to run in parallel whenever possible. ... -
2
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... -
3
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. -
4
CogVLM
A state-of-the-art open visual language model
CogVLM is an open-source visual–language model suite—and its GUI-oriented sibling CogAgent—aimed at image understanding, grounding, and multi-turn dialogue, with optional agent actions on real UI screenshots. The flagship CogVLM-17B combines ~10B visual parameters with ~7B language parameters and supports 490×490 inputs; CogAgent-18B extends this to 1120×1120 and adds plan/next-action outputs plus grounded operation coordinates for GUI tasks. -
Entity Management SoftwareAutomate everything: entity compliance, registered agent services, annual report and BOI filings, org charts, and DBA/fictitious name and business registration renewals, so you can focus on higher-value work.
-
5
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. ... -
6
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... -
7
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. ... -
8
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. ... -
9
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. -
Assembled is the only unified platform for staffing and managing your human and AI support team.Assembled is the only platform that unifies AI agents and intelligent workforce management to power fast and flexible support operations. Built for scale, we help teams automate over 50% of customer interactions, forecast with 90%+ accuracy, and optimize staffing across in-house and BPO teams. Orchestrate every chat, email, or call, balancing workloads between human and AI agents in real time — without sacrificing quality or control. Trusted by Stripe, Canva, and Robinhood, Assembled transforms support from a cost center into a strategic advantage. Our Workforce and Vendor Management tools connect forecasting, scheduling, and performance for smarter staffing decisions. AI Agents automate conversations across channels with your workflows and brand voice. AI Copilot empowers agents with real-time guidance, suggested replies, and one-click actions for faster, higher-quality resolutions.
-
10
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. -
11
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. -
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
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. -
14
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. -
15
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. -
16
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,...
-
17
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. -
18
higgsfield
Fault-tolerant, highly scalable GPU orchestration
Higgsfield is an open-source, fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters, such as Large Language Models (LLMs). -
19
Functionary
Chat language model that can use tools and interpret the results
Functionary is an open-source large language model specifically designed for interpreting and executing structured functions or external tools within conversational AI systems. The model extends traditional chat-based language models by enabling them to determine when external functions should be called and how to extract the necessary parameters from natural language input. -
20
YiVal
Your Automatic Prompt Engineering Assistant for GenAI Applications
YiVal is an open-source framework designed to automate prompt engineering and evaluation workflows for generative AI applications, enabling developers to systematically improve the performance of large language models. It focuses on experimentation and optimization by allowing users to test multiple prompt variations, configurations, and model parameters in parallel, then evaluate their outputs using structured metrics and scoring systems. The platform is particularly useful in production environments where prompt quality directly impacts user experience, as it provides a repeatable and data-driven approach to refining prompts rather than relying on manual trial and error. ... -
21
vits_chinese
Best practice TTS based on BERT and VITS
vits_chinese is an implementation of the VITS end-to-end text-to-speech (TTS) architecture tailored for Chinese (and possibly multilingual) speech synthesis. VITS is a model combining variational autoencoders (VAEs), normalizing flows, adversarial learning, and a stochastic duration predictor — a design that enables generation of natural, expressive speech, capturing variations in rhythm and prosody. By customizing or porting VITS for Chinese, this project aims to produce high-quality TTS... -
22
Petals
Run 100B+ language models at home, BitTorrent-style
Parallel inference reaches hundreds of tokens/sec. Beyond classic language model APIs — you can employ any fine-tuning and sampling methods, execute custom paths through the model, or see its hidden states. You get the comforts of an API with the flexibility of PyTorch. You can also host BLOOMZ, a version of BLOOM fine-tuned to follow human instructions in the zero-shot regime — just replace bloom-petals with bloomz-petals. -
23
Graph of Thoughts
Official Implementation of "Graph of Thoughts
...The framework executes these operations using a large language model as the reasoning engine while evaluating intermediate results to guide the search process. This approach enables models to explore multiple reasoning strategies in parallel and choose the most promising solutions during problem solving. -
24
Medusa
Framework for Accelerating LLM Generation with Multiple Decoding Heads
Medusa is a framework aimed at accelerating the generation capabilities of Large Language Models (LLMs) by employing multiple decoding heads. This approach allows for parallel processing during text generation, significantly enhancing throughput and reducing response times. Medusa is designed to be simple to implement and integrates with existing LLM infrastructures, making it a practical solution for scaling LLM applications. -
25
GPT-NeoX
Implementation of model parallel autoregressive transformers on GPUs
This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training. For those looking for a TPU-centric codebase, we...
