Search Results for "optimization" - Page 3
Sort By:
Showing 372 open source projects for "optimization"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
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.
-
1
ERNIE
The official repository for ERNIE 4.5 and ERNIEKit
...It supports both full-parameter training and parameter-efficient approaches so teams can choose between maximum quality and lower-cost adaptation depending on their constraints. 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. -
2
Nano-vLLM
A lightweight vLLM implementation built from scratch
...The project recreates the core functionality of vLLM in a simplified architecture written in approximately a thousand lines of Python, making it easier for developers and researchers to understand how modern LLM inference systems work. Despite its compact design, nano-vllm incorporates advanced optimization techniques such as prefix caching, tensor parallelism, and CUDA graph execution to achieve high performance during model inference. The engine is intended primarily for educational use, experimentation, and lightweight deployments where a full production-grade inference stack may be unnecessary. Its API closely mirrors that of the original vLLM framework, allowing developers familiar with vLLM to adopt the tool with minimal changes. -
3
LiteRT
LiteRT, successor to TensorFlow Lite
LiteRT is Google's next-generation on-device machine learning framework and the successor to TensorFlow Lite, designed for high-performance AI and generative AI deployment across edge devices. It provides efficient model conversion, optimization, and runtime execution while leveraging hardware acceleration from CPUs, GPUs, and NPUs. LiteRT supports a wide range of platforms, including Android, iOS, Linux, macOS, Windows, web environments, and IoT devices. The framework simplifies on-device AI development through automated accelerator selection, asynchronous execution, and optimized memory handling. ... -
4
Future AGI
Open-source platform for evaluating, observing, and improving LLM
Future AGI is an open-source, end-to-end platform for evaluating, observing, protecting, and improving AI agent applications. It is built for teams that need more than basic tracing, combining evaluations, simulations, datasets, guardrails, gateway routing, and optimization in one feedback loop. The platform helps developers detect hallucinations, measure agent quality, monitor production behavior, and use evaluation results to improve prompts or workflows over time. It supports both cloud and self-hosted deployment models, making it useful for teams with different privacy, infrastructure, and compliance needs. ... -
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.
-
5
Agent Executor (AX)
Google's open source distributed agent runtime
...It focuses on flexible model construction rather than a single fixed estimator, making it useful for researchers who want to experiment with different utility functions and optimization setups. ax is especially relevant for machine learning and econometrics workflows that need scalable, differentiable approaches to choice modeling. Its main value is giving researchers a modern, accelerator-friendly framework for estimating and analyzing discrete choice behavior. -
6
SwiftUI Agent Skill
SwiftUI agent skill for Claude Code, Codex, and other AI tools
...The system includes a comprehensive review process that evaluates code across multiple dimensions, including navigation, data flow, design compliance, and performance optimization. It is specifically tailored to align with current Apple development standards, including modern Swift versions and accessibility requirements like VoiceOver support. The tool integrates seamlessly with multiple AI coding environments, allowing developers to invoke it as part of their coding or review process. -
7
ComfyUI-Copilot
AI assistant for ComfyUI workflow generation, debugging, and tuning
...ComfyUI-Copilot focuses on reducing the complexity of building node-based pipelines for generative AI tasks such as image generation, making it more accessible to both beginners and experienced users. It supports the entire workflow lifecycle, including generation, debugging, rewriting, and parameter optimization, helping users iterate more efficiently. ComfyUI-Copilot leverages large language model capabilities to analyze user intent, recommend nodes, and suggest models that match specific requirements. It also provides automated error detection and repair suggestions, improving reliability during development. -
8
machine-learning-refined
Master the fundamentals of machine learning, deep learning
...Instead of presenting algorithms purely through mathematical derivations, the repository emphasizes geometric intuition, visualization, and step-by-step experimentation. It includes Jupyter notebooks and scripts that illustrate core machine learning topics such as regression, classification, optimization methods, and neural networks. These materials allow learners to see how algorithms behave during training and how different parameters affect model performance. -
9
MiniOneRec
Minimal reproduction of OneRec
...The framework provides an end-to-end pipeline for building generative recommender systems, including semantic identifier construction, supervised fine-tuning, and reinforcement learning-based optimization. Semantic IDs are created using techniques such as quantized variational autoencoders to convert item features into token sequences that can be modeled by transformer architectures. Developers can train and evaluate recommendation models using different backbone language models while benefiting from the generative framework’s parameter efficiency and scalability. -
$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.
-
10
how-to-optim-algorithm-in-cuda
How to optimize some algorithm in cuda
...Instead of presenting only theoretical explanations, the repository includes hand-written CUDA implementations of fundamental operations such as reductions, element-wise computations, softmax, and attention mechanisms. These examples show how different optimization techniques influence performance on modern GPU hardware and allow readers to experiment with real implementations. The repository also contains extensive learning notes that summarize CUDA programming concepts, GPU architecture details, and performance engineering strategies. -
11
Context Engineering
A frontier, first-principles handbook
Context Engineering is a comprehensive, open-source project serving as a first-principles handbook for the emerging discipline of context design and optimization in AI. Moving beyond traditional prompt engineering, this repository defines and explores how to craft and provide complete context payloads — not just single prompts — to large language models so they can perform tasks more reliably and intelligently. It takes inspiration from thought leaders like Andrej Karpathy and bridges theory with practical examples, offering structured guidance on context orchestration, memory, retrieval, and state control within AI workflows. ... -
12
DeepSeed
Deep learning optimization library making distributed training easy
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective. DeepSpeed delivers extreme-scale model training for everyone, from data scientists training on massive supercomputers to those training on low-end clusters or even on a single GPU. Using current generation of GPU clusters with hundreds of devices, 3D parallelism of DeepSpeed can efficiently train deep learning models with trillions of parameters. -
13
ort
Fast ML inference & training for ONNX models in Rust
...One of its key strengths is its flexibility, as it supports multiple backends and allows developers to configure execution providers depending on available hardware. ort also includes advanced capabilities such as model compilation and optimization, reducing startup time and improving runtime performance in production systems. -
14
mllm
Fast Multimodal LLM on Mobile Devices
...Implemented primarily in C and C++, it is designed to operate with minimal external dependencies while taking advantage of hardware-specific acceleration technologies such as ARM NEON and x86 AVX2 instructions. The system supports multiple optimization techniques including quantization, pruning, and speculative decoding to improve performance while reducing computational overhead. It also provides tools to convert models from popular formats like PyTorch checkpoints into optimized runtime formats that can be executed on supported hardware platforms. -
15
LightLLM
LightLLM is a Python-based LLM (Large Language Model) inference
...The framework enables developers to run and serve modern language models with significantly improved speed and resource efficiency compared to many traditional inference systems. Built primarily in Python, the project integrates optimization techniques and ideas from several leading open-source implementations, including FasterTransformer, vLLM, and FlashAttention, to accelerate token generation and reduce latency. LightLLM is designed to handle large-scale model workloads in production environments, supporting efficient batching and GPU utilization for fast inference across multiple requests. ... -
16
PyTorch-Tutorial-2nd
CV, NLP, LLM project applications, and advanced engineering deployment
...The project serves as a practical companion to a second edition of a PyTorch learning guide and is designed to help learners understand neural network concepts through hands-on coding examples. The repository covers a wide range of topics including tensor operations, neural network construction, model training workflows, and optimization strategies. It also introduces practical machine learning techniques such as convolutional neural networks, recurrent networks, and other architectures commonly used in modern AI applications. Each tutorial focuses on step-by-step implementation so learners can understand how theoretical concepts translate into working code. The materials are designed for both beginners and intermediate developers who want to gain practical experience building deep learning models using PyTorch. -
17
Xtuner
A Next-Generation Training Engine Built for Ultra-Large MoE Models
...Its architecture incorporates memory-efficient optimizations that allow researchers to train large models even when computational resources are limited. XTuner is also designed to integrate with modern AI ecosystems, supporting multimodal training, reinforcement learning optimization, and instruction tuning pipelines. -
18
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...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. The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. CUDA-Agent has demonstrated strong benchmark results, achieving high pass rates and significant speedups compared with compiler baselines such as torch.compile. -
19
Coze Loop
Next-generation AI Agent Optimization Platform
...The project aims to simplify the increasingly complex workflow of building reliable AI agents by offering integrated tools for debugging, evaluation, observability, and optimization. Through its visual playground, developers can test prompts interactively and compare outputs across different language models. The platform also includes automated evaluation capabilities that assess agent performance across multiple quality dimensions such as accuracy and compliance. Its observability layer captures detailed execution traces, enabling teams to understand how inputs, prompts, and tools interact during runtime. ... -
20
Web Quality Skills
Agent Skills for optimizing web quality based on Lighthouse
This repository is a curated set of AI agent skills that encapsulate best practices for improving web quality, performance, accessibility, search engine optimization, and general best practices for web projects. It encodes knowledge drawn from Google Lighthouse audits, Core Web Vitals heuristics, WCAG accessibility guidelines, and real-world engineering experience, allowing coding agents to automatically assess and suggest improvements. These skills are framework-agnostic, meaning they apply to React, Vue, Svelte, Angular, Astro, or even plain HTML projects. ... -
21
Agent Lightning
The absolute trainer to light up AI agents
Agent Lightning is an open-source framework developed by Microsoft to train and optimize AI agents using techniques like reinforcement learning (RL), supervised fine-tuning, and automatic prompt optimization, with minimal or zero changes to existing agent code. It’s designed to be compatible with a wide range of agent architectures and frameworks — from LangChain and OpenAI Agent SDKs to AutoGen and custom Python agents — making it broadly applicable across different agent tooling ecosystems. Agent-Lightning introduces a lightweight training pipeline that observes agents’ execution traces, converts them into structured data, and feeds them into training algorithms, enabling users to improve agent behaviors systematically. ... -
22
Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO
Agent Reinforcement Trainer, or ART is an open-source reinforcement learning framework tailored to training large language model agents through experience, making them more reliable and performant on multi-turn, multi-step tasks. 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. -
23
Prompt Optimizer
A prompt word optimizer to help write high-quality prompt words
Prompt-Optimizer is a high-impact AI prompt engineering tool designed to help users craft better, more effective prompts for large language models, boosting the quality and relevance of AI responses. It focuses on automating and streamlining the iterative refinement of prompts by analyzing examples, comparing original and optimized text, and guiding users through multi-round improvements that surface clarity, structure, and specificity. With support for different deployment modes including... -
24
LLM Course
Course to get into Large Language Models (LLMs)
...Learners get exposure to multiple adaptation strategies—LoRA/QLoRA, instruction fine-tuning, and alignment techniques—so they can choose approaches that fit their hardware and budgets. The materials also cover inference optimization and quantization to make serving LLMs feasible on commodity GPUs or even CPUs, which is crucial for side projects and startups. Evaluation is treated as a first-class topic, with examples of automatic and human-in-the-loop methods to catch regressions and verify quality beyond simple loss values. By the end, students have a mental model and a practical toolkit for iterating on datasets, training configs, etc. -
25
Axon
Nx-powered Neural Networks
...Functional API – A low-level API of numerical definitions (defn) of which all other APIs build on. Model Creation API – A high-level model creation API which manages model initialization and application. Optimization API – An API for creating and using first-order optimization techniques based on the Optax library. Training API – An API for quickly training models, inspired by PyTorch Ignite. Axon provides abstractions that enable easy integration while maintaining a level of separation between each component. You should be able to use any of the APIs without dependencies on others. ...
