Search Results for "deep" - Page 18
Sort By:
Showing 1152 open source projects for "deep"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
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.
-
1
Torch Pruning
DepGraph: Towards Any Structural Pruning
Torch-Pruning is an open-source toolkit designed to optimize deep neural networks by performing structural pruning directly within PyTorch models. The library focuses on reducing the size and computational cost of neural networks by removing redundant parameters and channels while maintaining model performance. It introduces a graph-based algorithm called DepGraph that automatically identifies dependencies between layers, allowing parameters to be pruned safely across complex architectures. ... -
2
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs
FastDeploy is an open-source inference and deployment toolkit designed to simplify the process of running and serving deep learning models across a wide range of hardware platforms. Developed within the PaddlePaddle ecosystem, the toolkit focuses on providing high-performance deployment capabilities for modern AI models including large language models and vision-language systems. The platform enables developers to deploy trained models quickly using optimized inference pipelines that support GPUs, specialized AI accelerators, and other hardware architectures. ... -
3
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. ... -
4
AWS Agent Skills
AWS Skills for Agents
AWS Agent Skills is a repository that curates AWS-focused agent skills — capability modules that give AI assistants like Claude Code and Codex deep, practical knowledge across key Amazon Web Services domains. Instead of streaming giant documentation sets or relying on episodic web search, this project compresses AWS best practices, usage patterns, edge cases, and real-world engineering guides into pre-structured skill definitions that are token-efficient and tailored for reasoning. ... -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
5
Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO
...Instead of just manually crafting prompts or relying on supervised fine-tuning, ART uses techniques like Group Relative Policy Optimization (GRPO) to let agents learn from environmental feedback and reward signals. The framework is designed to integrate easily with Python applications, abstracting much of the RL infrastructure so developers can train agents without deep RL expertise or heavy infrastructure overhead. ART also supports scalable training patterns, observability tools, and integration with hosted platforms like Weights & Biases, and it provides notebooks that demonstrate training on standard benchmarks and tasks. -
6
FinRobot
An Open-Source AI Agent Platform for Financial Analysis using LLMs
...It provides developers and quants with structured modules to fetch market data, process time series, generate technical indicators, and construct features appropriate for machine learning models, while also supporting backtesting and evaluation metrics to measure strategy performance. Built with modularity in mind, FinRobot allows users to plug in custom models — from classical algorithms to deep learning architectures — and orchestrate components in pipelines that can run reproducibly across experiments. The framework also tends to include automation layers for deployment, enabling trained models to operate in live or simulated environments with scheduled re-training and risk controls in place. -
7
Step3-VL-10B
Multimodal model achieving SOTA performance
...It achieves this efficiency and strong performance through unified pre-training on a massive 1.2 trillion-token multimodal corpus that jointly optimizes a language-aligned perception encoder with a powerful decoder, creating deep synergy between image processing and text understanding. -
8
Cloud Cost Handbook
Set of guides meant to help explain often-times complex pricing
...The handbook covers core concepts, pricing examples, cost-optimization techniques, and billing models across providers such as AWS, Azure, and GCP, with each section curated to improve clarity and accessibility for readers without deep financial or cloud billing expertise. Because it’s hosted on GitHub and open to contributions, anyone from beginners to experts can add insights, examples, and updated pricing patterns as cloud offerings evolve. -
9
PythonPark
Python open source project "The Road to Self-Study Programming"
PythonPark is a large, curated “learning playground” for Python — essentially a comprehensive self-study meta-repository aimed at helping learners progress in Python programming, data science, machine learning, web scraping, and software engineering practices. It aggregates tutorials, learning guides, project examples, and resources across topics: from Python basics and data structures to machine learning, web scraping, and even interview preparation and “programmer life” guidance. Because... -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
10
Shumai
Fast Differentiable Tensor Library in JavaScript & TypeScript with Bun
...Built on Bun and Flashlight, with ArrayFire as its numerical backend, Shumai brings GPU-accelerated tensor operations, automatic differentiation, and scientific computing tools directly to JavaScript developers. It allows seamless integration of machine learning, deep learning, and custom differentiable programs into web-based or server-side environments without relying on Python frameworks. The library supports matrix operations, gradient computation, and tensor conversions with intuitive APIs and near-native speed, thanks to Bun’s low-overhead FFI bindings. It can automatically leverage GPU acceleration on Linux (via CUDA) and CPU computation on macOS. -
11
MobileLLM
MobileLLM Optimizing Sub-billion Parameter Language Models
...Introduced in the ICML 2024 paper “MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases”, it focuses on delivering strong reasoning and generalization capabilities in models under one billion parameters. The framework integrates several architectural innovations—SwiGLU activation, deep and thin network design, embedding sharing, and grouped-query attention (GQA)—to achieve a superior trade-off between model size, inference speed, and accuracy. MobileLLM demonstrates remarkable performance, with the 125M and 350M variants outperforming previous state-of-the-art models of the same scale by up to 4.3% on zero-shot commonsense reasoning tasks. -
12
3FS
A high-performance distributed file system
The 3FS repository (standing likely for “Feature 3F System” or similar) is focused on providing a feature extraction and transformation framework tailored to deep and large models, especially in token-based systems. Its primary aim is to support efficient and scalable feature transformation pipelines—especially for inference environments—by batching, caching, and integrating feature-based modules like segmenters, sparse retrievers, and scorers seamlessly. The repo includes APIs to define components (e.g. seg, ret, scor) that wrap or interface with external or internal modules, as well as logic to schedule and compose these feature transforms. ... -
13
BISHENG
BISHENG is an open LLM devops platform for next generation apps
BISHENG is an open LLM application DevOps platform, focusing on enterprise scenarios. It has been used by a large number of industry-leading organizations and Fortune 500 companies. "Bi Sheng" was the inventor of movable type printing, which played a vital role in promoting the transmission of human knowledge. We hope that BISHENG can also provide strong support for the widespread implementation of intelligent applications. Everyone is welcome to participate. -
14
PySR
High-Performance Symbolic Regression in Python and Julia
...Here, one essentially uses symbolic regression to convert a neural net to an analytic equation. Thus, these tools simultaneously present an explicit and powerful way to interpret deep neural networks. -
15
crwlr
Library for Rapid (Web) Crawler and Scraper Development
...Or it can be restricted to load only links matching certain criteria (on same domain/host, URL path starts with "/foo",...) or only to a certain depth. A depth of 3 means 3 levels deep. Links found on the initial URLs provided to the crawler are level 1 and so on. -
16
Soufflé
Datalog variant for tool designers crafting analyses in Horn clauses
Rapid prototyping for your analysis problems with logic; enabling deep design-space explorations; designed for large-scale static analysis; e.g., points-to analysis for Java, taint-analysis, and security checks. Futamura projections/partial evaluation for effective translation to parallel C++; optimized staged compilation; specialized data-structures for logical relations. Efficient translation to parallel C++ of Datalog programs (CAV'16, CC'16) Efficient interpretation using de-specialization techniques (PLDI'21) Specialized data structure for relations (PACT'19, PPoPP'19, PMAM'19) with optimal index selection (VLDB'18) Extended semantics of Datalog, e.g., permitting unbounded recursions with numbers and terms. ... -
17
goldmark
A markdown parser written in Go. Easy to extend, standard, compliant
...Easy to extend, standard(CommonMark) compliant, well structured.golang-commonmark may be a good choice, but it seems to be a copy of markdown-it. blackfriday.v2 is a fast and widely-used implementation, but is not CommonMark-compliant and cannot be extended from outside of the package, since its AST uses structs instead of interfaces. Furthermore, its behavior differs from other implementations in some cases, especially regarding lists: Deep nested lists don't output correctly #329, List block cannot have a second line #244, etc. This behavior sometimes causes problems. If you migrate your Markdown text from GitHub to blackfriday-based wikis, many lists will immediately be broken. As mentioned above, CommonMark is complicated and hard to implement, so Markdown parsers based on CommonMark are few and far between. -
18
Buffalo
Rapid Web Development w/ Go
...Use the Webpack-generated configuration to build your frontend assets, so you can optimize both the backend and frontend. Code, save, refresh. Use the buffalo dev command to rebuild your app, from backend to frontend, and just see the changes live! Deep integration with pop provides a simple way to handle databases and common-related tasks. Supported databases: MySQL/MariaDB, PostgreSQL, CockroachDB, SQLite. -
19
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... -
20
buku
Personal mini-web in text
...Hence, buku. buku can import bookmarks from the browser(s) or fetch the title, tags and description of a URL from the web. Use your favorite editor to add, compose and update bookmarks. Search bookmarks instantly with multiple search options, including regex and a deep scan mode (handy with URLs). It can look up broken links on Wayback Machine. There's an Easter Egg to revisit random bookmarks. There's no tracking, hidden history, obsolete records, usage analytics or homing. To get started right away, jump to the Quickstart section. buku has one of the best documentation around. The man page comes with examples. -
21
Komiser
Cloud environment inspector
Stay under budget by uncovering hidden costs, monitoring increases in spending, and making impactful changes based on customer recommendations. Komiser CE is a free and Open Source project with the goal to create an open cloud cost optimization project with the support of all major public cloud providers. In the last months, we’ve more than doubled our OSS downloads and expanded our community footprint. This is possible because the tool works solves real problems, and is embraced by... -
22
Koila
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code
Koila is a lightweight Python library designed to help developers avoid memory errors when training deep learning models with PyTorch. The library introduces a lazy evaluation mechanism that delays computation until it is actually required, allowing the framework to better estimate the memory requirements of a model before execution. By building a computational graph first and executing operations only when necessary, koila reduces the risk of running out of GPU memory during the forward pass of neural network training. ... -
23
Swift Concurrency Agent Skill
Add expert Swift Concurrency guidance to your AI coding tool
Swift Concurrency Agent Skill is an open-source “agent skill” designed to give AI coding assistants deep expertise in Apple’s Swift Concurrency model, including async/await, structured concurrency, task groups, actors, and thread safety. It is formatted according to the Agent Skills specification so that tools like Claude Code, Cursor, Copilot, and other LLM-powered systems can load it and apply guidance when relevant. The skill codifies practical best practices for writing efficient, safe, and modern concurrent Swift code and outlines how to modernize existing legacy code toward Swift 6 conventions. ... -
24
IQuest-Coder-V1 Model Family
New family of code large language models (LLMs)
IQuest-Coder-V1 is a cutting-edge family of open-source large language models specifically engineered for code generation, deep code understanding, and autonomous software engineering tasks. These models range from tens of billions to smaller footprints and are trained on a novel code-flow multi-stage paradigm that captures how real software evolves over time — not just static code snapshots — giving them a deeper semantic understanding of programming logic. -
25
FastRTC
The python library for real-time communication
...FastRTC also integrates nicely with UI frameworks (e.g. via a web demo using Gradio), so developers can rapidly prototype and deploy real-time streaming applications without deep knowledge of low-level WebRTC internals. Because voice-enabled AI agents often involve many moving parts (speech-to-text, text processing, text-to-speech, streaming, session/chat management), FastRTC helps by handling the streaming aspect, leaving the rest to be plugged in modularly.
