Search Results for "compute" - Page 7
Sort By:
Showing 646 open source projects for "compute"
View related business solutions-
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.
-
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
EPLB
Expert Parallelism Load Balancer
...The logic is implemented in eplb.py and supports predicting placements given estimated expert usage weights. EPLB aims to reduce hot-spotting and ensure more uniform usage of compute resources in large MoE deployments. -
2
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... -
3
BertViz
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
...The model view shows a bird's-eye view of attention across all layers and heads. The neuron view visualizes individual neurons in the query and key vectors and shows how they are used to compute attention. -
4
NATS Go Client
Golang client for NATS, the cloud native messaging system
...With the ability to process millions of messages a second per server, you’ll find unparalleled efficiency with NATS. Save money by minimizing cloud costs with reduced compute and network usage for streams, services, and eventing. NATS self-heals and can scale up, down, or handle topology changes anytime with zero downtime to your system. Clients require zero awareness of NATS topology allowing you future proof your system to meet your needs of today and tomorrow. -
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
5
AWS SDK for Go v2
AWS SDK for the Go programming language
Welcome to the AWS SDK for Go. The AWS SDK for Go V2 provides APIs and utilities that developers can use to build Go applications that use AWS services, such as Amazon Elastic Compute Cloud (Amazon EC2) and Amazon Simple Storage Service (Amazon S3). The SDK removes the complexity of coding directly against a web service interface. It hides a lot of the lower-level plumbing, such as authentication, request retries, and error handling. The SDK also includes helpful utilities. For example, the Amazon S3 download and upload manager can automatically break up large objects into multiple parts and transfer them in parallel. ... -
6
Colab-MCP
An MCP server for interacting with Google Colab
...Instead of relying on manual notebook usage, the system allows MCP-compatible agents to execute code, manage files, install dependencies, and orchestrate entire development workflows within Colab’s cloud infrastructure. This approach bridges the gap between local AI agents and remote high-performance compute environments, allowing users to offload heavy workloads such as machine learning training, data analysis, and dependency-heavy tasks to Colab’s GPU and TPU resources. By exposing Colab as an MCP server, the tool enables seamless integration with a wide range of AI assistants and agent frameworks, creating a standardized interface for tool use and execution. -
7
Ploomber
The fastest way to build data pipelines
Ploomber is an open-source framework designed to simplify the development and deployment of data science and machine learning pipelines. It allows developers to transform exploratory data analysis workflows into production-ready pipelines without rewriting large portions of code. The system integrates with common development environments such as Jupyter Notebook, VS Code, and PyCharm, enabling data scientists to continue working with familiar tools while building scalable workflows. Ploomber... -
8
Paddler
Open-source LLM load balancer and serving platform for hosting LLMs
...The system acts as a specialized load balancer and serving layer for language models, enabling organizations to run inference workloads without relying on external API providers. It supports running models locally through engines such as llama.cpp while distributing requests across multiple compute nodes to improve performance and reliability. The architecture is designed with privacy and cost control in mind, making it suitable for organizations that handle sensitive data or require predictable operational costs. Paddler also includes tools for monitoring, request buffering, and autoscaling integration so that deployments can adapt dynamically to changing workloads. ... -
9
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... -
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
LLMs-from-scratch is an educational codebase that walks through implementing modern large-language-model components step by step. It emphasizes building blocks—tokenization, embeddings, attention, feed-forward layers, normalization, and training loops—so learners understand not just how to use a model but how it works internally. The repository favors clear Python and NumPy or PyTorch implementations that can be run and modified without heavyweight frameworks obscuring the logic. Chapters... -
11
Granite 3.0 Language Models
New set of lightweight state-of-the-art, open foundation models
This repository introduces Granite 3.0 language models as lightweight, state-of-the-art open foundation models built to natively support multilinguality, coding, reasoning, and tool usage. A central goal is efficient deployment, including the potential to run on constrained compute resources while remaining useful for a broad span of enterprise tasks. The repo positions the models for both research and commercial use under an Apache-2.0 license, signaling permissive adoption paths. Documentation highlights the capability mix (reasoning, tool use, code) and points to model artifacts and guidance for evaluation. ... -
12
MetaCLIP
ICLR2024 Spotlight: curation/training code, metadata, distribution
...The repository provides training logic, adaptation strategies (e.g. prompt tuning, adapter modules), and evaluation across base and target domains to measure how well the model retains its general knowledge while specializing as needed. It includes utilities to fine-tune vision-language embeddings, compute prompt or adapter updates, and benchmark across transfer and retention metrics. MetaCLIP is especially suited for real-world settings where a model must continuously incorporate new visual categories or domains over time. -
13
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
...The repository provides training recipes, data pipelines, and evaluation utilities for image JEPA variants and often includes ablations that illuminate which masking and architectural choices matter. Because the objective is non-autoregressive and operates in embedding space, JEPA tends to be compute-efficient and stable at scale. The approach has become a strong alternative to contrastive or pixel-reconstruction methods for representation learning. -
14
Profile Data
Analyze computation-communication overlap in V3/R1
profile-data is a repository that publishes profiling traces and metrics from DeepSeek’s training and inference infrastructure (especially during DeepSeek-V3 / R1 experiments). The profiling data targets insights into computation-communication overlap, pipeline scheduling (e.g. DualPipe), and how MoE / EP / parallelism strategies interact in real systems. The repository contains JSON trace files like train.json, prefill.json, decode.json, and associated assets. Users can load them into tools... -
15
future
R package: future: Unified Parallel and Distributed Processing in R
...It allows R expressions to be scheduled for future evaluation, with the result retrieved later, in a way decoupled from the specific backend used. This lets code be written in a way that works with sequential execution, multicore, multisession, cluster, or remote compute backends, without changing the high-level code. It handles automatic exporting of needed global variables/functions, managing of packages, RNG, etc. Automatic detection and export of global objects and functions needed by future expressions, so the user doesn’t need to manage that manually. Ability to control how futures are resolved. -
16
mlr3
mlr3: Machine Learning in R - next generation
mlr3 is a modern, object-oriented R framework for machine learning. It provides core abstractions (tasks, learners, resamplings, measures, pipelines) implemented using R6 classes, enabling extensible, composable machine learning workflows. It focuses on clean design, scalability (large datasets), and integration into the wider R ecosystem via extension packages. Users can do classification, regression, survival analysis, clustering, hyperparameter tuning, benchmarking etc., often via... -
17
PML
The easiest way to use deep metric learning in your application
This library contains 9 modules, each of which can be used independently within your existing codebase, or combined together for a complete train/test workflow. To compute the loss in your training loop, pass in the embeddings computed by your model, and the corresponding labels. The embeddings should have size (N, embedding_size), and the labels should have size (N), where N is the batch size. The TripletMarginLoss computes all possible triplets within the batch, based on the labels you pass into it. ... -
18
Amazon CodeGuru Profiler Python Agent
Amazon CodeGuru Profiler Python Agent
Amazon CodeGuru Profiler collects runtime performance data from your live applications and provides recommendations that can help you fine-tune your application performance. Using machine learning algorithms, CodeGuru Profiler can help you find your most expensive lines of code and suggest ways you can improve efficiency and remove CPU bottlenecks. CodeGuru Profiler provides different visualizations of profiling data to help you identify what code is running on the CPU, see how much time is... -
19
AWS CodeDeploy Agent
Host Agent for AWS CodeDeploy
AWS CodeDeploy is a fully managed deployment service that automates software deployments to a variety of compute services such as Amazon EC2, AWS Fargate, AWS Lambda, and your on-premises servers. AWS CodeDeploy makes it easier for you to rapidly release new features, helps you avoid downtime during application deployment, and handles the complexity of updating your applications. You can use AWS CodeDeploy to automate software deployments, eliminating the need for error-prone manual operations. ... -
20
Alluxio
Open Source Data Orchestration for the Cloud
...It bridges the gap between computation frameworks and storage systems, bringing data from the storage tier closer to the data driven applications. This enables applications to connect to numerous storage systems through a common interface. It makes data local, more accessible and as elastic as compute. -
21
IMS Toucan
Controllable and fast Text-to-Speech for over 7000 languages
...It is the official home of ToucanTTS, a massively multilingual TTS system designed to support over 7,000 languages with a single unified framework. The toolkit focuses on being fast and controllable while not requiring huge amounts of compute, making it practical for research labs and smaller teams. It includes complete pipelines for preprocessing datasets, training models, and running inference, plus a storage configuration system to manage where models and caches are stored. IMS-Toucan ships with several ready-to-run scripts, including GUIs for interactive demos, prosody override tools, zero-shot language embedding injection, and text-to-audio file generation. ... -
22
SuperDuperDB
Integrate, train and manage any AI models and APIs with your database
Build and manage AI applications easily without needing to move your data to complex pipelines and specialized vector databases. Integrate AI and vector search directly with your database including real-time inference and model training. Just using Python. A single scalable deployment of all your AI models and APIs which is automatically kept up-to-date as new data is processed immediately. No need to introduce an additional database and duplicate your data to use vector search and build on... -
23
gpt-oss-safeguard
Safety reasoning models built-upon gpt-oss
...The model comes in at least two variants: a large 120B-parameter version for heavy-duty, high-accuracy reasoning, and a 20B-parameter version optimized for lower latency or smaller compute resources. At inference time you supply both the content and your own safety policy (written in a structured prompt), and the model will evaluate the content and return its justification — enabling transparent, auditable moderation decisions. It supports running fully locally or in private infrastructure (no mandatory cloud dependence). -
24
VibeThinker
Diversity-driven optimization and large-model reasoning ability
VibeThinker is a compact but high-capability open-source language model released by WeiboAI (Sina AI Lab). It contains about 1.5 billion parameters, far smaller than many “frontier” models, yet it is explicitly optimized for reasoning, mathematics, and code generation tasks rather than general open-domain chat. The innovation lies in its training methodology: the team uses what they call the Spectrum-to-Signal Principle (SSP), where a first stage emphasizes diversity of reasoning paths (the... -
25
MetricFlow
MetricFlow allows you to define, build, and maintain metrics in code
...It works alongside a data stack—typically built with dbt—and allows you to express metrics as YAML‐based definitions tied to semantic models and dimension tables, rather than embedding logic ad-hoc across many dashboards or scripts. When a user or tool requests a metric (e.g., “monthly revenue by region”), MetricFlow generates optimized, warehouse-specific SQL to compute that metric, handling joins, filters, time grains, offsets, and other complexities under the hood. Because metric definitions live centrally, you avoid duplication across teams and tools, reduce risk of inconsistent numbers, and make it easier to audit and evolve the logic over time. The project emphasizes explainability, performance and portability: you define metrics once and then they can be consumed in BI tools, notebooks, or even AI/agent-driven workflows.
