Search Results for "gpu max performance" - Page 7
Sort By:
Showing 458 open source projects for "gpu max performance"
View related business solutions-
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.
-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
1
DINOv3
Reference PyTorch implementation and models for DINOv3
DINOv3 is the third-generation iteration of Meta’s self-supervised visual representation learning framework, building upon the ideas from DINO and DINOv2. It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while... -
2
xFormers
Hackable and optimized Transformers building blocks
xformers is a modular, performance-oriented library of transformer building blocks, designed to allow researchers and engineers to compose, experiment, and optimize transformer architectures more flexibly than monolithic frameworks. It abstracts components like attention layers, feedforward modules, normalization, and positional encoding, so you can mix and match or swap optimized kernels easily. One of its key goals is efficient attention: it supports dense, sparse, low-rank, and... -
3
shimmy
Python-free Rust inference server
...This compatibility enables developers to replace remote AI services with locally hosted models while keeping their existing software architecture intact. Shimmy focuses on performance and simplicity, using efficient runtime components to minimize memory usage and startup time compared to heavier inference frameworks. It supports modern model formats such as GGUF and SafeTensors and can automatically discover models stored locally or in common directories used by other AI tools. Advanced capabilities include CPU offloading for Mixture-of-Experts models and GPU acceleration, enabling large models to run on consumer hardware with limited VRAM. -
4
LightLLM
LightLLM is a Python-based LLM (Large Language Model) inference
LightLLM is a high-performance inference and serving framework designed specifically for large language models, focusing on lightweight architecture, scalability, and efficient deployment. The framework enables developers to run and serve modern language models with significantly improved speed and resource efficiency compared to many traditional inference systems. -
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
5
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. -
6
DLRM
An implementation of a deep learning recommendation model (DLRM)
...The architecture combines dense (MLP) and sparse (embedding) branches, then interacts features via dot product or feature interactions before passing through further dense layers to predict click-through, ranking scores, or conversion probabilities. The implementation is optimized for performance at scale, supporting multi-GPU and multi-node execution, quantization, embedding partitioning, and pipelined I/O to feed huge embeddings efficiently. It includes data loaders for standard benchmarks (like Criteo), training scripts, evaluation tools, and capabilities like mixed precision, gradient compression, and memory fusion to maximize throughput. -
7
MoCo (Momentum Contrast)
Self-supervised visual learning using momentum contrast in PyTorch
...The core idea of MoCo is to maintain a dynamic dictionary with a momentum-updated encoder, allowing efficient contrastive learning across large batches. The repository includes implementations for both MoCo v1 and MoCo v2, the latter improving training stability and performance through architectural and augmentation enhancements. Training is optimized for distributed multi-GPU environments, using DistributedDataParallel for speed and simplicity. -
8
CTranslate2
Fast inference engine for Transformer models
CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. ... -
9
OpenFold
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction
OpenFold carefully reproduces (almost) all of the features of the original open source inference code (v2.0.1). The sole exception is model ensembling, which fared poorly in DeepMind's own ablation testing and is being phased out in future DeepMind experiments. It is omitted here for the sake of reducing clutter. In cases where the Nature paper differs from the source, we always defer to the latter. OpenFold is trainable in full precision, half precision, or bfloat16 with or without... -
Add Two Lines of Code. Get Full APM.Works out of the box for Rails, Django, Express, Phoenix, and more. Monitoring exceptions and performance in no time.
-
10
Face Alignment
2D and 3D Face alignment library build using pytorch
...By default, the package will use the SFD face detector. However, the users can alternatively use dlib, BlazeFace, or pre-existing ground truth bounding boxes. While not required, for optimal performance(especially for the detector) it is highly recommended to run the code using a CUDA-enabled GPU. While here the work is presented as a black box, if you want to know more about the intrisecs of the method please check the original paper either on arxiv or my webpage. -
11
Halide
A language for fast, portable data-parallel computation
Halide is a programming language for fast, portable data-parallel computation. It was designed to make writing high-performance image and array processing code much easier on modern machines. It works on all major operating systems and with several CPU architectures (X86, ARM, MIPS, Hexagon, PowerPC) and GPU Compute APIs (CUDA, OpenCL, OpenGL, among others). It isn't a standalone programming language however; rather it is embedded in C++ which means that you write C++ code, building an in-memory representation of a Halide pipeline using Halide's C++ API. ... -
12
MNN
MNN is a blazing fast, lightweight deep learning framework
...Android platform, core so size is about 400KB, OpenCL so is about 400KB, Vulkan so is about 400KB. Supports hybrid computing on multiple devices. Currently supports CPU and GPU. -
13
GPUPixel
Real-time image and video processing library similar to GPUImage
GPUPixel is a real-time image and video processing library written in C++11, based on OpenGL/ES. It offers functionalities similar to GPUImage, including built-in beauty filters, enabling efficient processing and rendering of visual effects on images and videos. -
14
PyOpenCL
OpenCL integration for Python, plus shiny features
PyOpenCL is a Python wrapper for the OpenCL framework, providing seamless access to parallel computing on CPUs, GPUs, and other accelerators. It enables developers to harness the full power of heterogeneous computing directly from Python, combining Python’s ease of use with the performance benefits of OpenCL. PyOpenCL also includes convenient features for managing memory, compiling kernels, and interfacing with NumPy, making it a preferred choice in scientific computing, data analysis, and... -
15
HunyuanWorld-Voyager
RGBD video generation model conditioned on camera input
HunyuanWorld-Voyager is a next-generation video diffusion framework developed by Tencent-Hunyuan for generating world-consistent 3D scene videos from a single input image. By leveraging user-defined camera paths, it enables immersive scene exploration and supports controllable video synthesis with high realism. The system jointly produces aligned RGB and depth video sequences, making it directly applicable to 3D reconstruction tasks. At its core, Voyager integrates a world-consistent video... -
16
pmxt
A unified API for trading across prediction markets
PMXT is a powerful, cross-platform terminal emulator and multiplexer designed to enhance productivity for command-line users by seamlessly blending terminal emulation with workspace management. It lets you run multiple shell sessions in panes and tabs, detach and reattach to workspaces, and persist session layouts—making it ideal for developers, sysadmins, and power users who juggle many concurrent tasks. PMXT also includes built-in features like customizable keybindings, layout presets, and... -
17
DeepSpeed MII
MII makes low-latency and high-throughput inference possible
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed. The Deep Learning (DL) open-source community has seen tremendous growth in the last few months. Incredibly powerful text generation models such as the Bloom 176B, or image generation model such as Stable Diffusion are now available to anyone with access to a handful or even a single GPU through platforms such as Hugging Face. While open-sourcing has democratized access to AI capabilities, their application is... -
18
ngx-toastr
Angular Toastr
Toast Component Injection without being passed ViewContainerRef. No use of ngFor. Fewer dirty checks and higher performance. AoT compilation and lazy loading compatible. Component inheritance for custom toasts. SystemJS/UMD rollup bundle. Animations using Angular's Web Animations API. Output toasts to an optional target directive. Put toasts in a specific div inside your application. This should probably be somewhere that doesn't get deleted. Add ToastContainerModule to the ngModule where... -
19
ds4.c
DeepSeek 4 Flash local inference engine for Metal
...The engine includes DS4-specific model loading, KV cache management, prompt rendering, and OpenAI-compatible server APIs for local deployment workflows. Built as a native low-level implementation, it focuses on performance, reduced abstraction overhead, and direct integration with Apple GPU acceleration through Metal compute graphs. The project also supports streaming inference behavior and local API serving for integration with external tools and AI applications. Overall, ds4 represents a minimalist high-performance approach to running large language models locally without relying on heavyweight inference frameworks. -
20
dots.ocr
Multilingual Document Layout Parsing in a Single Vision-Language Model
dots.ocr is a cutting-edge multilingual document parsing system built on a unified vision-language model that combines layout detection, text recognition, and structural understanding into a single architecture. Unlike traditional OCR pipelines that rely on multiple specialized components, dots.ocr integrates these processes end-to-end, reducing error propagation and improving consistency across tasks. The model is designed to recognize virtually any human script, making it highly effective... -
21
Mosec
A high-performance ML model serving framework, offers dynamic batching
Mosec is a high-performance and flexible model-serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. -
22
ERNIE
The official repository for ERNIE 4.5 and ERNIEKit
ERNIE is an open-source large-model toolkit and model family from the PaddlePaddle ecosystem that focuses on training, fine-tuning, compression, and practical application of ERNIE large language models. The repository positions ERNIEKit as an industrial-grade development toolkit, emphasizing end-to-end workflows that span high-performance pre-training, supervised fine-tuning, and alignment. 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. ... -
23
GitHub Actions for DigitalOcean
GitHub Actions for DigitalOcean - doctl
...Powerful and production-ready, our cloud platform has the solutions that devs like you need to succeed, whether you're building world-changing AI apps, running a side project, or building a business. GPU solutions for everyone—novice to expert. Run training and inference, process large data sets and complex neural networks, and deploy high-performance computing clusters. -
24
Compute Library
The Compute Library is a set of computer vision and machine learning
The Compute Library is a set of computer vision and machine learning functions optimized for both Arm CPUs and GPUs using SIMD technologies. The library provides superior performance to other open-source alternatives and immediate support for new Arm® technologies e.g. SVE2. -
25
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
Qwen2.5-Omni is an end-to-end multimodal flagship model in the Qwen series by Alibaba Cloud, designed to process multiple modalities (text, images, audio, video) and generate responses both as text and natural speech in streaming real-time. It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds...
