Search Results for "gpu hardware" - Page 2
Sort By:
Showing 88 open source projects for "gpu hardware"
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.
-
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.
-
1
WanGP
AI video generator optimized for low VRAM and older GPUs use
Wan2GP is an open source AI video generation toolkit designed to make modern generative models accessible on consumer-grade hardware with limited GPU memory. It acts as a unified interface for running multiple video, image, and audio generation models, including Wan-based models as well as other systems like Hunyuan Video, Flux, and Qwen. A key focus of the project is reducing VRAM requirements, enabling some workflows to run on as little as 6 GB while still supporting older Nvidia and certain AMD GPUs. ... -
2
FlashKDA
High-performance Kimi Delta Attention kernels
FlashKDA is an open-source library of high-performance CUDA kernels for Kimi Delta Attention, implemented on NVIDIA CUTLASS. It is intended to accelerate the forward pass used by KDA-based language models on modern NVIDIA GPUs. The package integrates with flash-linear-attention and can be selected automatically as the backend for chunk_kda during inference. It supports recurrent state input and output, variable-length batches, internal gating, query-key normalization, and beta activation.... -
3
Train LLM From Scratch
A straightforward method for training your LLM
...The repository walks through the process from downloading data to generating text with a trained model. It supports training smaller or larger models, including million- and billion-parameter configurations depending on available hardware. A major goal is accessibility, since the author frames it as possible to train models using a single GPU. It is most useful for learners, researchers, and developers who want practical exposure to LLM internals. -
4
TensorRT Node for ComfyUI
Enables the best performance on NVIDIA RTX Graphics Cards
...The repo typically includes instructions for converting models to TensorRT engines and for wiring those engines into ComfyUI nodes. This is particularly attractive for power users who run many generations or who host ComfyUI on dedicated hardware and want to squeeze out every bit of GPU performance. In short, it’s about taking ComfyUI from “it runs” to “it runs fast” on NVIDIA GPUs. -
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.
-
5
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... -
6
Ollama Telegram Bot
Ollama Telegram bot, with advanced configuration
...It includes access control features such as user whitelists and admin roles, allowing fine-grained control over who can interact with the bot and manage its behavior. The bot connects to a local or remote Ollama server, enabling users to run models on their own hardware while maintaining full privacy. It supports Docker-based deployment, making it easy to set up alongside an Ollama instance with optional GPU acceleration. Configuration is handled through environment variables, allowing customization of models, timeouts, and interaction rules. Overall, ollama-telegram provides a lightweight and extensible solution for deploying personal or team-based AI assistants. -
7
Stable Diffusion Version 2
High-Resolution Image Synthesis with Latent Diffusion Models
...The repository provides code for training and running Stable Diffusion-style models, instructions for installing dependencies (with notes about performance libraries like xformers), and guidance on hardware/driver requirements for efficient GPU inference and training. It’s organized as a practical, developer-focused toolkit: model code, scripts for inference, and examples for using memory-efficient attention and related optimizations are included so researchers and engineers can run or adapt the model for their own projects. The project sits within a larger ecosystem of Stability AI repositories (including inference-only reference implementations like SD3.5 and web UI projects) and the README points users toward compatible components, recommended CUDA/PyTorch versions. -
8
Bailing
Bailing is a voice dialogue robot similar to GPT-4o
...The project is modular: each core function — ASR, VAD, LLM, TTS — exists as a separately replaceable component, which allows flexibility in picking your preferred models depending on resources or languages. It aims to be light enough to run without a GPU, making it usable on modest hardware or edge devices, while still maintaining low latency and smooth interaction. Bailing includes a memory system, giving the assistant the ability to remember user preferences and context across sessions, which enables more personalized and context-aware conversations. -
9
Wan2.1
Wan2.1: Open and Advanced Large-Scale Video Generative Model
...Wan2.1 focuses on efficient video synthesis while maintaining rich semantic and aesthetic detail, enabling applications in content creation, entertainment, and research. The model supports text-to-video and image-to-video generation tasks with flexible resolution options suitable for various GPU hardware configurations. Wan2.1’s architecture balances generation quality and inference cost, paving the way for later improvements seen in Wan2.2 such as Mixture-of-Experts and enhanced aesthetics. It was trained on large-scale video and image datasets, providing generalization across diverse scenes and motion patterns. -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
Lemonade
Lemonade helps users run local LLMs with the highest performance
Lemonade is a local LLM runtime that aims to deliver the highest possible performance on your own hardware by auto-configuring state-of-the-art inference engines for both NPUs and GPUs. The project positions itself as a “local LLM server” you can run on laptops and workstations, abstracting away backend differences while giving you a single place to serve and manage models. Its README emphasizes real-world adoption across startups, research groups, and large companies, signaling a focus on... -
11
mosaicml composer
Supercharge Your Model Training
composer is a deep learning training framework built on PyTorch and designed to make large-scale model training more efficient, scalable, and customizable. At the center of the project is a highly optimized Trainer abstraction that simplifies the management of training loops, parallelization, metrics, logging, and data loading. The framework is intended for modern workloads that may span anything from a single GPU to very large distributed training environments, which makes it suitable for... -
12
TensorRT LLM
TensorRT LLM provides users with an easy-to-use Python API
TensorRT-LLM is an open-source high-performance inference library specifically designed to optimize and accelerate large language model deployment on NVIDIA GPUs. It provides a Python-based API built on top of PyTorch that allows developers to define, customize, and deploy LLMs efficiently across a variety of hardware configurations, from single GPUs to large multi-node clusters. The library focuses on maximizing throughput and minimizing latency through advanced techniques such as... -
13
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... -
14
JAX Toolbox
Public CI, Docker images for popular JAX libraries
JAX Toolbox is a development toolkit designed to streamline and optimize the use of JAX for machine learning and high-performance computing on NVIDIA GPUs. It provides prebuilt Docker images, continuous integration pipelines, and optimized example implementations that help developers quickly set up and run JAX workloads without complex configuration. The project supports popular JAX-based frameworks and models, including architectures used for large-scale pretraining such as GPT and LLaMA... -
15
Style-Bert-VITS2
Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles
...It includes a full GUI editor to script dialogue, set different styles per line, edit dictionaries, and save/load projects, plus a separate web UI and Colab notebooks for training and experimentation. For those who only need synthesis, the project is published as a Python library (pip install style-bert-vits2) and can run on CPU without an NVIDIA GPU, though training still requires GPU hardware. -
16
Intel Extension for PyTorch
A Python package for extending the official PyTorch
Intel® Extension for PyTorch* extends PyTorch* with up-to-date features optimizations for an extra performance boost on Intel hardware. Optimizations take advantage of Intel® Advanced Vector Extensions 512 (Intel® AVX-512) Vector Neural Network Instructions (VNNI) and Intel® Advanced Matrix Extensions (Intel® AMX) on Intel CPUs as well as Intel Xe Matrix Extensions (XMX) AI engines on Intel discrete GPUs. Moreover, Intel® Extension for PyTorch* provides easy GPU acceleration for Intel discrete GPUs through the PyTorch* xpu device. -
17
CogVideo
Text and image to video generation: CogVideoX and CogVideo
CogVideo is an open-source family of advanced video generation models that can create videos from text, images, or existing video inputs. Built on large-scale Transformer and diffusion architectures, it enables multimodal generation across text-to-video, image-to-video, and video continuation tasks. The latest CogVideoX models offer higher resolution outputs, longer video durations, and improved controllability through prompt engineering. The project includes tools for inference,... -
18
LocalGPT
Chat with your documents on your local device using GPT models
LocalGPT is a private, on-premises document intelligence platform for questioning, summarizing, and analyzing files with locally hosted language models. Its data remains on the user’s machine, making it suitable for confidential or offline workflows. The retrieval system combines semantic similarity, keyword matching, late chunking, contextual enrichment, and sentence-level pruning. A smart router chooses between retrieval-augmented generation and direct model responses for each query. An... -
19
Microduck RL
RL training environments for Microduck (mjlab)
...Its sim-to-real setup models actuator physics, backlash, domain randomization, and reward design. Trained policies can be exported to ONNX and deployed through the separate Microduck runtime. Training normally uses CUDA hardware, while supported workflows can offload jobs to Hugging Face Jobs when a local GPU is unavailable. -
20
Real-Time Voice Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Real-Time Voice Cloning is an influential deep-learning repository that demonstrates how to clone a voice from just a few seconds of audio and then generate arbitrary speech in that voice in near real time. It implements the SV2TTS pipeline (“Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis”) in three stages: a speaker encoder, a synthesizer, and a vocoder. In the first stage, short audio clips are converted into a fixed-dimensional speaker embedding that... -
21
SimpleLLM
950 line, minimal, extensible LLM inference engine built from scratch
SimpleLLM is a minimal, extensible large language model inference engine implemented in roughly 950 lines of code, built from scratch to serve both as a learning tool and a research platform for novel inference techniques. It provides the core components of an LLM runtime—such as tokenization, batching, and asynchronous execution—without the abstraction overhead of more complex engines, making it easier for developers and researchers to understand and modify. Designed to run efficiently on... -
22
Unsloth-MLX
Bringing the Unsloth experience to Mac users via Apple's MLX framework
...This project removes traditional barriers that prevent Mac users from prototyping and experimenting with LLM training locally by allowing the same code used in cloud GPU environments to run on M-series hardware, improving workflow continuity and reducing iteration costs. It supports loading and training Hugging Face models with fine-tuning strategies like SFT, DPO, ORPO, and GRPO and even handles exporting models to formats like GGUF for downstream use, although some limitations apply with quantized models. ... -
23
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
gpt-oss is OpenAI’s open-weight family of large language models designed for powerful reasoning, agentic workflows, and versatile developer use cases. The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. Both models use a native MXFP4 quantization for efficient memory use and support OpenAI’s Harmony response format, enabling transparent full chain-of-thought reasoning and advanced tool integrations such as function calling, browsing, and Python code execution. ... -
24
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. ... -
25
Diffrax
Numerical differential equation solvers in JAX
Diffrax is a numerical differential equation solving library built for the JAX ecosystem, with a strong focus on composability, differentiability, and high-performance scientific computing. The project provides tools for solving ordinary differential equations, stochastic differential equations, controlled differential equations, and related systems in a way that fits naturally into modern machine learning and differentiable programming workflows. Because it is written to work closely with...
