Search Results for "memory" - Page 34
Sort By:
Showing 3192 open source projects for "memory"
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.
-
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.
-
1
Tiny CUDA Neural Networks
Lightning fast C++/CUDA neural network framework
...We provide a sample application where an image function (x,y) -> (R,G,B) is learned. The fully fused MLP component of this framework requires a very large amount of shared memory in its default configuration. It will likely only work on an RTX 3090, an RTX 2080 Ti, or high-end enterprise GPUs. Lower-end cards must reduce the n_neurons parameter or use the CutlassMLP (better compatibility but slower) instead. tiny-cuda-nn comes with a PyTorch extension that allows using the fast MLPs and input encodings from within a Python context. ... -
2
tinysearch
Tiny, full-text search engine for static websites built with Rust
...It is written in Rust and compiled to WebAssembly, allowing it to run entirely in the browser while maintaining a very small footprint. The engine uses compact data structures such as XOR filters to efficiently index and query text, significantly reducing memory usage compared to traditional search libraries. TinySearch is particularly well-suited for blogs and documentation sites generated by static site generators, where simplicity and performance are critical. It processes content into a serialized binary index that can be loaded quickly and searched client-side, eliminating the need for external search services. ... -
3
RISC-V sandboxing library
The fastest RISC-V sandbox
RISC-V sandboxing library is a high-performance, ultra-low-latency RISC-V userspace emulator library written in modern C++, designed for embedding and sandboxing applications. Unlike full-system emulators, it focuses specifically on executing user-space programs, making it ideal for scenarios such as sandboxed execution, scripting engines, and high-performance server environments. The library is engineered to achieve extremely fast startup and execution times, with the ability to run large... -
4
BeeAI Framework
Build production-ready AI agents in both Python and Typescript
BeeAI Framework is an open-source, production-grade toolkit designed for building intelligent AI agents and complex multi-agent systems that can reason, act, and collaborate to solve real-world problems at scale. It goes beyond simple prompt-based interactions by introducing rule-based governance and constraint enforcement, enabling developers to create agents with predictable and controllable behavior while still preserving advanced reasoning capabilities. The framework supports both Python... -
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.
-
5
deepjazz
Deep learning driven jazz generation using Keras & Theano
...The repository demonstrates how machine learning can learn musical structure and produce original compositions. It uses the Keras and Theano libraries to build a two-layer Long Short-Term Memory network capable of learning temporal patterns in music. The system analyzes musical sequences from an input MIDI file and then generates new musical notes that follow similar stylistic patterns. The project was originally created during a hackathon and was designed to show how neural networks can emulate creative tasks traditionally associated with human musicians. ... -
6
rust-bert
Rust native ready-to-use NLP pipelines and transformer-based models
...The project ports many capabilities of the Hugging Face Transformers ecosystem into the Rust programming language. It allows developers to run state-of-the-art NLP models like BERT, GPT-2, and DistilBERT directly within Rust applications while maintaining high performance and memory efficiency. The library integrates with Rust machine learning infrastructure using crates such as tch-rs and ONNX Runtime for model execution. It also includes tokenization utilities, model architectures, and task-specific pipelines that simplify the development of NLP applications. Because Rust is known for its safety and performance, this project enables developers to deploy modern NLP models in production systems written in Rust. -
7
RTP-LLM
Alibaba's high-performance LLM inference engine for diverse apps
...The system focuses on improving throughput, latency, and resource utilization when running large models in production environments. It achieves this by implementing optimized GPU kernels, batching strategies, and memory management techniques tailored for transformer inference workloads. The framework is designed for large-scale AI services and is already used internally across several Alibaba platforms such as Taobao, Amap, and other business systems that rely on conversational or search-related AI services. RTP-LLM supports a wide variety of modern model architectures, including Qwen, DeepSeek, and Llama-based models, making it a flexible engine for deploying many different open-source LLMs. -
8
LLM-Pruner
On the Structural Pruning of Large Language Models
LLM-Pruner is an open-source framework designed to compress large language models through structured pruning techniques while maintaining their general capabilities. Large language models often require enormous computational resources, making them expensive to deploy and inefficient for many practical applications. LLM-Pruner addresses this issue by identifying and removing non-essential components within transformer architectures, such as redundant attention heads or feed-forward... -
9
Agentic Context Engine
Make your agents learn from experience
...In this workflow, one component generates solutions, another reflects on outcomes, and a third curates useful knowledge so it can be reused in future interactions. This architecture allows agents to gradually build persistent operational memory without requiring additional training datasets or model retraining. -
$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
MatMul-Free LM
Implementation for MatMul-free LM
...The architecture relies on quantization-aware training and lightweight operations to replace conventional dense matrix multiplications with more efficient alternatives. These optimizations can significantly reduce memory consumption and potentially improve computational efficiency during both training and inference. The repository provides implementations of models at several parameter scales and includes tools for experimenting with the architecture using modern machine learning frameworks. -
11
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.... -
12
Chitu
High-performance inference framework for large language models
...Chitu is designed to scale from small single-machine deployments to large distributed clusters that handle high volumes of concurrent inference requests. The system also includes performance optimizations for large models, including support for quantized formats and efficient computation operators that reduce memory usage and latency. Its architecture aims to support enterprise adoption by ensuring stable long-term operation under production workloads. -
13
lms
LM Studio CLI
lms is a command-line interface tool designed to interact with and manage local large language models through the LM Studio ecosystem. The tool allows developers to control model execution directly from the terminal, providing programmatic access to features that are otherwise available through graphical interfaces. Through the CLI, users can load and unload models, start or stop local inference servers, and inspect the inputs and outputs generated by language models. LMS is built using the... -
14
LuxTTS
A high-quality rapid TTS voice cloning model
...Intended for developers, hobbyists, and creators, the repository includes installation instructions, usage examples, and Python APIs that make it feasible to integrate the model in local workflows, web demos, or production systems. Its design emphasizes efficiency and practicality, fitting within modest GPU memory footprints. -
15
Nano Events
Simple and tiny (107 bytes) event emitter library for JavaScript
Nano Events is a minimalistic, high-performance event emitter library for JavaScript. Its goal is to provide the simplest possible API to add pub/sub capabilities (emitters and listeners) to any JS object or application, while keeping overhead and bundle size extremely small. Rather than offering many complex features, nanoevents focuses on the core primitives: creating an emitter, subscribing to named events, emitting events with arbitrary data, and unsubscribing. Because of its minimal API... -
16
imgui_club
Nice things to use along dear imgui
imgui_club is a companion collection to Dear ImGui that gathers small, officially maintained extensions and illustrative samples that don’t belong in the core library but are broadly useful. Instead of being a monolithic add-on, it focuses on targeted utilities that demonstrate patterns, widgets, and techniques the author and community rely on in real projects. You’ll find examples that show how to structure multi-context rendering, deal with threading concerns, and compose immediate-mode... -
17
s2n-quic
An implementation of the IETF QUIC protocol
...QUIC is a UDP-based, multiplexed, encrypted transport layer that underpins HTTP/3 and addresses issues such as head-of-line blocking and faster handshake times compared to TCP+TLS. This library integrates with AWS’s s2n-tls or rustls for the TLS 1.3 handshake and leverages Rust’s memory and thread safety guarantees to deliver a robust implementation. It is built with configurability in mind—you can tune congestion control (like CUBIC), pacing, packet size discovery, and other advanced network behaviors. Extensive testing (unit, fuzz, interop) ensures protocol compliance and interoperability with other implementations. ... -
18
Autocxx
Tool for safe ergonomic Rust/C++ interop driven from existing C++
...With autocxx, developers can include C++ headers directly in Rust source code and automatically generate bindings for the corresponding C++ classes, functions, and types. This approach greatly simplifies working with existing C++ libraries in Rust while maintaining safety and memory correctness. By reducing the amount of boilerplate and manual configuration typically needed for FFI (Foreign Function Interface) bindings, autocxx allows developers to focus on higher-level logic rather than low-level integration details. -
19
syzkaller
syzkaller is an unsupervised coverage-guided kernel fuzzer
...It automatically generates, mutates, and minimizes system call programs, then drives them through a specialized executor (syz-executor) to exercise deep kernel paths. The system integrates tightly with sanitizers such as KASAN, KMSAN, KCSAN, and UBSAN to surface memory safety, concurrency, and undefined behavior issues with actionable reports. A distributed architecture coordinates many fuzzing VMs, collects crash signatures, deduplicates them, and bisects to the first bad commit when possible. syzkaller maintains per-kernel “syz” descriptions so it understands arguments, flags, and resources of thousands of syscalls and ioctls across Linux and other kernels. ... -
20
gVisor
Application Kernel for Containers
gVisor is an application kernel developed by Google that provides a strong layer of isolation between applications and the host operating system. Written in Go, it implements a Linux-compatible system call interface that runs entirely in user space, creating a secure sandboxed environment for containers. Unlike traditional virtual machines or lightweight syscall filters, gVisor follows a third approach that offers many of the security benefits of virtualization while maintaining the speed,... -
21
DBHub
Universal database MCP server connecting to MySQL, PostgreSQL
...Configuration is environment-variable driven, with a DSN and per-engine settings covering Postgres, MySQL, MariaDB, SQL Server, and SQLite. Operational flags include read-only mode, row limits, and even SSH tunneling options for secure access into private networks. A demo mode ships with an in-memory SQLite “employee” dataset so users can try the tools immediately without provisioning a database. The project lives in the Bytebase org alongside database DevSecOps tooling, underscoring a production focus on safe and auditable DB interaction. -
22
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
LMCache is an extension layer for LLM serving engines that accelerates inference, especially with long contexts, by storing and reusing key-value (KV) attention caches across requests. Instead of rebuilding KV states for repeated or shared text segments, LMCache persists and retrieves them from multiple tiers—GPU memory, CPU DRAM, and local disk—then injects them into subsequent requests to reduce TTFT and increase throughput. Its design supports reuse beyond strict prefix matching and enables sharing across serving instances, improving efficiency under real multi-tenant traffic. The broader project includes examples, tests, a server component, and public posts describing cross-engine sharing and inter-GPU KV transfers. ... -
23
MobileLLM
MobileLLM Optimizing Sub-billion Parameter Language Models
MobileLLM is a lightweight large language model (LLM) framework developed by Facebook Research, optimized for on-device deployment where computational and memory efficiency are critical. 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. ... -
24
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
...It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding names to match different model contexts. It also offers extension mechanisms so that custom encodings can be registered. Internally, it includes the core tokenizer logic (often implemented in Rust or efficient lower-level code), APIs for encoding, decoding, and counting tokens, and binding layers to Python (and sometimes other languages) for easy use. -
25
Cpp17
Chinese translation of C++17 The Complete Guide
...The content is organized into multiple parts: basic language features (e.g. structured binding, inline variables, enhanced switch, lambdas), template and compile-time features (e.g. fold expressions, class template argument deduction, constexpr improvements), and the additions to the standard library (e.g. std::optional, std::variant, std::string_view, file system, concurrency, and parallel algorithms). It also covers enhancements to existing STL components, new library utilities, and advanced topics like polymorphic memory resources (PMR), alignment, and generic programming improvements.