LLM Inference & Serving

A unified interface for LLMs.

A high-throughput and memory-efficient inference and serving engine for LLMs.

A fast serving framework for large language models and vision language models.

The AI community building the future.

The fastest way to build with Gemini.

Get up and running with large language models.

LLM inference in C/C++

Bring Grok to your computer.

Build with OpenAI

The AI Acceleration Cloud

Fine-tune LLMs and VLMs faster with less memory.

The easiest way to build and scale generative AI applications with foundation models.

The generative media platform for developers

Meet Claude, your thinking partner

Fast AI inference for open models

One API for all AI models.

The inference platform for AI products.

Diffusion-based speculative decoding for faster LLM inference

Meta Model API public preview

Local AI app and inference engine for agents.

State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation

Build real-time, natural conversations with Gemini.

Discover, download, and run local LLMs.

Everything to power your Hermes Agent

Desktop AI supercomputer for AI developers.

AI inference microservices

High-performance serving framework for omni-modal models.

Open-source RL training with ZoRRo acceleration

AI-native application development platform

Build on the Claude Platform

Claude on AWS with native billing, IAM, and Managed Agents

The best coding agents run on Baseten

Automatically select the best model for each task.

The fastest way to build with generative AI

High-performance linear attention kernels built on TileLang.

The AI platform for work.

An asynchronous reinforcement-learning framework for large language models

ModelScope: discover and use AI models, datasets, and applications.

Fast inference for coding agents

A 128GB unified-memory AI PC platform with 1 PFLOP of FP4 compute

Guarantee long-term access to OpenAI compute.

Fast speech recognition with NVIDIA's Parakeet models in pure C++.

Enabling robots to understand, remember, and act.

Open infrastructure for AI research and superintelligence.

Inference optimization endpoint targeting lower-cost execution while preserving reference-model behavior.

Open-source TileLang kernels for DeepSeek workloads

A full-stack platform for open superintelligence.

Serverless inference for frontier open-weight models focused on long horizon agentic workloads.

Continual Learning After Deployment

AFM model playground

AI agents for your enterprise

One API. 300+ AI Models. All the power you need.

A one-stop generative AI development platform.

Enterprise platform for customizing and deploying efficient language models.

AI computing SuperPoD for large-scale AI training and high-concurrency inference

一站式人工智能开发平台

LLM API for Baidu AI Studio

AI models and products built for real work

The fastest AI inference

Use Claude Code as the unified interface for all your LLMs.

Best Subscription for Open Weight Models.

Build and deploy AI applications on Cloudflare's global network.

Cloudflare Workers AI provider for the AI SDK.

A comprehensive LLM serving solution

The first AI that can earn its own existence, replicate, and evolve — without needing a human.

Bring PyTorch models to Core AI for on-device execution.

CUDA is NVIDIA's parallel computing platform and programming model.

The Data Intelligence Platform

Turn Deployed AI into Runtime Intelligence

DeepSeek R1 + Claude = DeepClaude

A high-performance expert-parallel communication library.

Clean and Efficient FP8 GEMM Library

A tool for condensed AI/ML model architecture summaries.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Run your own AI cluster at home with everyday devices.

Fine-tune open source models.

Metadata-driven adaptation of vision foundation models for scientific domains.

Bringing Flash Magic to Classical Machine Learning Operators

Efficient MLA decoding kernels for Hopper GPUs.

High-throughput tensor loading for PyTorch -- load models at up to 25Gbps without GDS.

A fully AI-generated pretraining framework.

Pure Rust local OCR for agents

Speak it. See it. Share it.

Coding-focused access to GLM models

Run AI models locally on your Android device.

Chat with local LLMs, privately.

Fast AI inference in the cloud

Superpowers for Claude Code

Benchmark LLM inference performance

The platform for scalable, reliable, and efficient inference

A model built for deterministic tasks

The Universal Gateway for AI Inference

The full-stack platform for training your own models

Control every model call

Long Context Pre-Training with Lighthouse Attention

Idea to AI product, ⚡️ fast.

One API to call all LLM APIs

LM Studio’s headless daemon

Use your local models, remotely.

Supercharge your LLM with KV Cache.

Multimodal AI software product

Augment your apps with AI

Build your frontier with Studio.

One AI API, flattened parameters.

AI infrastructure that runs everywhere.

A KVCache-centric disaggregated architecture for LLM serving.

Ship Apps. Agents. Companies. One prompt. One config file. All your infrastructure.

Scalable reinforcement learning for LLM post-training.

AI Model Aggregation Management and Distribution System

Runtime for AI agents to execute real-world tasks

Efficient and accurate low-precision inference.

The AI supercomputer for every enterprise.

Free AI Image & Video Studio

A fully open-source framework for instruction tuning and preference tuning of LMs.

Open-source specification and ecosystem for building multi-provider, interoperable LLM interfaces.

Open-source theoretical reconstruction of the Claude Mythos Recurrent-Depth Transformer architecture

Optimizing LLMs.

One gateway. Every model.

AI Toolkit

Everything your inference stack is missing.

Machine Learning Platform for AI

A lightweight text-to-speech model.

PrismML platform

Define functions in English. Run them locally.

Native NVIDIA CUDA kernels for Ampere and newer GPUs.

Build fast, scalable, and cost-effective LLM services.

A coding agent you can leave running.

Advancing biological preparedness with trusted developers and government partners.

The Cloud Built for AI

Edge AI platform

Open Medical Superintelligence

Launch, manage, and stop LLM inference workloads on one or more NVIDIA DGX Spark systems — no Slurm, no Kubernetes, no fuss.

From Coding to Agents, Build It All

Amortized KV Cache Compaction in a Single Forward Pass

The full-stack communications platform.

AI inference at the speed you want and the margin you need

Compute for every scale.

Thinking Machines software platform

A domain-specific language designed to streamline the development of high-performance GPU kernels for AI workloads.

Ascend TileLang adapter

Train Dreambooth models. Generate unlimited AI assets.

Automatic model routing for lower LLM spend.

Run and train AI models locally with Unsloth Studio.

The world's largest GPU marketplace.

Private, unrestricted access to all the leading AI models across text, image, video, and audio, behind one API key.

Production inference for encoders, poolers, and structured prediction — as vLLM plugins.

One API for all AI models.