Search Results for "cpu" - Page 13
Sort By:
Showing 1449 open source projects for "cpu"
View related business solutions-
$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.
-
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.
-
1
Z80-μLM
Z80-μLM is a 2-bit quantized language model
Z80-μLM is a retro-computing AI project that demonstrates a tiny language model (Z80-μLM) engineered to run on an 8-bit Z80 CPU by aggressively quantizing weights down to 2-bit precision. The repository provides a complete workflow where you train or fine-tune conversational models in Python, then export them into a format that can be executed on classic Z80 systems. A key deliverable is producing CP/M-compatible .COM binaries, enabling a genuinely vintage “chat with your computer” experience on real hardware or accurate emulators. ... -
2
RamaLama
Simplifies the local serving of AI models from any source
RamaLama is an open-source developer tool that simplifies working with and serving AI models locally or in production by leveraging container technologies like Docker, Podman, and OCI registries, allowing AI inference workflows to be treated like standard container deployments. It abstracts away much of the complexity of configuring AI runtimes, dependencies, and hardware optimizations by detecting available GPUs (or falling back to CPU) and automatically pulling a container image pre-configured for the detected hardware environment. Developers can use familiar container commands to pull, run, and interact with AI models from any source, treating models similarly to how container images are handled in OCI workflows. RamaLama supports multiple model registries and offers a REST API or chatbot interface for interacting with running models, making it flexible for local development, testing, or integration into larger systems. -
3
whisper-timestamped
Multilingual Automatic Speech Recognition with word-level timestamps
Multilingual Automatic Speech Recognition with word-level timestamps and confidence. Whisper is a set of multi-lingual, robust speech recognition models trained by OpenAI that achieve state-of-the-art results in many languages. Whisper models were trained to predict approximate timestamps on speech segments (most of the time with 1-second accuracy), but they cannot originally predict word timestamps. This repository proposes an implementation to predict word timestamps and provide a more... -
4
Core ML Tools
Core ML tools contain supporting tools for Core ML model conversion
...Your app uses Core ML APIs and user data to make predictions, and to fine-tune models, all on the user’s device. Core ML optimizes on-device performance by leveraging the CPU, GPU, and Neural Engine while minimizing its memory footprint and power consumption. Running a model strictly on the user’s device removes any need for a network connection, which helps keep the user’s data private and your app responsive. -
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
Android Contacts, Reborn
Android Contacts API Library written in Kotlin
This library provides a complete set of APIs to do everything you need with Contacts in Android. You no longer have to deal with the Contacts Provider, database operations, and cursors. Whether you just need to get all or some Contacts for a small part of your app (written in Kotlin or Java), or you are looking to create your own full-fledged Contacts app with the same capabilities as the AOSP Android Contacts app and Google Contacts app, this library is for you. -
6
Grafana Pyroscope
Continuous Profiling Platform. Debug performance issues
...FlameQL enables custom queries to select and aggregate profiles quickly and efficiently for easy analysis. Analyze application performance profiles using our suite of profiling tools. Understand usage of CPU and memory resources at any point in time and identify performance issue before your customer do. Collect, store, and analyze profiles from various external profiling tools in one central location. Link to your Open Telemetry tracing data and get request-specific or span-specific profiles to enhance other observability data like traces and logs. -
7
observer_cli
Visualize Erlang/Elixir Nodes On The Command Line
...Total scheduler utilization will equal 1.0 when all schedulers have been active all the time between the two refresh intervals. The result being that there is a decent chunk of CPU usage that would be mostly free for scheduling actual Erlang work (assuming the schedulers are busy waiting more than trying to select tasks to run). -
8
Fluent Bit Amazon Kinesis Firehose
A Fluent Bit output plugin for Amazon Kinesis Data Firehose
...However, we are pausing development on it and will focus on the high-performance version instead. If the features of the higher performance plugin are sufficient for your use cases, please use it. It can achieve higher throughput and will consume less CPU and memory. This plugin has been tested with Fluent Bit 1.2.0+. It may not work with older Fluent Bit versions. We recommend using the latest version of Fluent Bit as it will contain the newest features and bug fixes. We distribute a container image with Fluent Bit and these plugins. -
9
ArrayFire
ArrayFire, a general purpose GPU library
...Together we can fulfill The ArrayFire Mission under an excellent Code of Conduct that promotes a respectful and friendly building experience. Rigorous benchmarks and tests ensuring top performance and numerical accuracy. Cross-platform compatibility with support for CUDA, OpenCL, and native CPU on Windows, Mac, and Linux. Built-in visualization functions through Forge. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
Binaryen
Compiler infrastructure and toolchain library for WebAssembly
...It accepts input in WebAssembly-like form but also accepts a general control flow graph for compilers that prefer that. Binaryen's internal IR uses compact data structures and is designed for completely parallel codegen and optimization, using all available CPU cores. Binaryen's IR also compiles down to WebAssembly extremely easily and quickly because it is essentially a subset of WebAssembly. Binaryen's optimizer has many passes (see an overview later down) that can improve code size and speed. These optimizations aim to make Binaryen powerful enough to be used as a compiler backend by itself. -
11
Typecho Blogging Platform
A PHP blogging platform, simple and powerful
With only 7 data tables and less than 400KB of code, a complete plug-in and template mechanism is complete. Ultra-low CPU and memory usage is enough to give full play to the maximum performance of the host. Native support for Markdown typesetting syntax, easy to read and write. Support various cloud hosts such as BAE/GAE/SAE, even in the face of sudden high traffic, it can easily cope with it. The meticulously polished operation interface is still a familiar feature, but more mature and with more options. ... -
12
rav1e
The fastest and safest AV1 encoder
rav1e is an open-source implementation of an encoder for the AV1 video codec, developed in Rust (with some assembly) by the community around Xiph Foundation. Its design philosophy is to start from a correct, minimal, and fast AV1 encoder — sacrificing some encoding speed/efficiency of reference encoders in exchange for simplicity, stability, and compilability across platforms — and then gradually improve. This makes rav1e particularly attractive for scenarios where you need AV1 encoding but... -
13
DocArray
The data structure for multimodal data
...Data science powerhouse: greatly accelerate data scientists’ work on embedding, k-NN matching, querying, visualizing, evaluating via Torch/TensorFlow/ONNX/PaddlePaddle on CPU/GPU. Data in transit: optimized for network communication, ready-to-wire at anytime with fast and compressed serialization in Protobuf, bytes, base64, JSON, CSV, DataFrame. Perfect for streaming and out-of-memory data. One-stop k-NN: Unified and consistent API for mainstream vector databases. -
14
Jittor
Jittor is a high-performance deep learning framework
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators. The whole framework and meta-operators are compiled just in time. A powerful op compiler and tuner are integrated into Jittor. It allowed us to generate high-performance code specialized for your model. Jittor also contains a wealth of high-performance model libraries, including image recognition, detection, segmentation, generation, differentiable rendering, geometric learning, reinforcement... -
15
AutomatedLab
Framework that lets you deploy complex labs on HyperV and Azure
...There are only two requirements you need to make sure: You need the DVD ISO images and a Hyper-V host or an Azure subscription. Requires Windows Management Framework 5+ (Windows). Requires Intel VT-x or AMD/V capable CPU, a decent amount of RAM, and low-latency high-throughput storage (No spinning disks please, as there are issues related to them). This solution supports setting up virtual machines with Windows 7, 2008 R2, 8 / 8.1 and 2012 / 2012 R2, 10 / 2016, 2019, and SQL Server 2008, 2008R2, 2012, 2014, 2016, 2017, 2019. -
16
GPU Hot
Real-time NVIDIA GPU dashboard
GPU Hot is an open-source, lightweight monitoring dashboard designed to provide real-time visibility into NVIDIA GPU performance across single machines or entire clusters. The project offers a self-hosted web interface that streams hardware metrics directly from GPU servers, enabling developers, ML engineers, and system administrators to observe GPU utilization and system behavior in real time through a browser. The dashboard collects and displays a wide range of performance metrics... -
17
VibeTensor
Our first fully AI generated deep learning system
VibeTensor is a groundbreaking open-source research system software stack for deep learning that was uniquely generated almost entirely by AI coding agents under guided human supervision, demonstrating a new frontier in AI-assisted software engineering. It implements a PyTorch-style eager tensor library with a modern C++20 core that supports both CPU and CUDA backends, giving it the ability to manage tensors, automatic differentiation (autograd), and complex computation flows similar to mainstream frameworks. What makes VibeTensor remarkable is that every major component, from core libraries and dispatch systems to CUDA runtime support, caching allocators, and language bindings, was created and validated by coding agents using automated builds and tests rather than manual line-by-line human coding. ... -
18
bitnet.cpp
Official inference framework for 1-bit LLMs
bitnet.cpp is the official open-source inference framework and ecosystem designed to enable ultra-efficient execution of 1-bit large language models (LLMs), which quantize most model parameters to ternary values (-1, 0, +1) while maintaining competitive performance with full-precision counterparts. At its core is bitnet.cpp, a highly optimized C++ backend that supports fast, low-memory inference on both CPUs and GPUs, enabling models such as BitNet b1.58 to run without requiring enormous... -
19
Sopro TTS
A lightweight text-to-speech model with zero-shot voice cloning
Sopro TTS is an open-source text-to-speech (TTS) project that implements a lightweight model capable of producing speech from text with zero-shot voice cloning, meaning it can mimic a speaker’s voice from only a few seconds of reference audio. Built with a 169 million-parameter architecture that uses dilated convolutions and cross-attention layers instead of large Transformer stacks, it achieves relatively fast real-time performance even on CPUs (about a 0.25 real-time factor measured on an... -
20
Wuffs
Wrangling Untrusted File Formats Safely
...The design prioritizes predictable performance: decoders avoid dynamic allocation by default, return explicit “short read” signals, and run well in streaming or sandbox-free environments. The project ships battle-tested, CPU-friendly implementations for common image/container formats and bit-twiddly primitives like Huffman and checksum routines. Its standard library emphasizes portability and constant-time behavior where appropriate, which is valuable in security-sensitive contexts. Because the language is purpose-built, the resulting C output is small, auditable, and easy to embed in larger systems. -
21
RLax
Library of JAX-based building blocks for reinforcement learning agents
...It supports both on-policy and off-policy learning, as well as value-based, policy-based, and model-based approaches. RLax is fully JIT-compilable with JAX, enabling high-performance execution across CPU, GPU, and TPU backends. The library implements tools for Bellman equations, return distributions, general value functions, and policy optimization in both continuous and discrete action spaces. It integrates seamlessly with DeepMind’s Haiku (for neural network definition) and Optax (for optimization), making it a key component in modular RL pipelines. -
22
Infinity
Low-latency REST API for serving text-embeddings
Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting all sentence-transformer models and frameworks. Infinity is developed under MIT License. Infinity powers inference behind Gradient.ai and other Embedding API providers. -
23
Coroot
Open-source observability for microservices
...Understand your cloud costs down to any given application. Doesn't require access to your cloud account or any other configurations. Analyze any unexpected spike in CPU or memory usage down to the precise line of code. Don't make assumptions, know exactly what the resources were spent on. Easily investigate any anomaly by comparing it to the system's baseline behavior. -
24
OpenCost
Cost monitoring for Kubernetes workloads and cloud costs
OpenCost is a vendor-neutral open-source project for measuring and allocating cloud infrastructure and container costs in real-time. Built by Kubernetes experts and supported by Kubernetes practitioners, OpenCost shines a light into the black box of Kubernetes spending. Flexible, customizable cost allocation and cloud resource monitoring for accurate showback, chargeback, and ongoing reporting. Dynamic asset pricing, through integrations with AWS, Azure, and GCP billing APIs as well as... -
25
Axe
Logger-agnostic wrapper that normalizes logs regardless of arg style
...Great for large dev teams, old/new projects, and works w/Pino, Bunyan, Winston, console, and more. It is lightweight, performant, highly-configurable, and automatically adds OS, CPU, and Git information to your logs. Hooks, dot-notation remap, omit, and pick of metadata. Axe was built to provide consistency among development teams when it comes to logging. You not only have to worry about your development team using the same approach to writing logs and debugging applications, but you also have to consider that open-source maintainers implement logging differently in their packages. ...