Model Inference Hosting

Zhipu AI ChatGLM

Software

Chinese foundation model and assistant platform.

KServe

MLOps Platforms

Kubernetes-based model inference platform for standardized serverless serving of machine learning models.

Nebius

Cloud Infrastructure

AI cloud platform formerly part of Yandex offering full-stack AI infrastructure and managed services.

Nous Research

Developer Tools

AI research collective building open-source fine-tuned language models including Hermes and Capybara series for the developer community.

On-demand GPU cloud for AI model training and inference workloads.

Pylonix

Edge Computing Platforms

Edge cloud for running customer-facing AI workloads in user data planes.

Friendli

Software

Generative AI engine platform for serving LLMs with optimized inference performance.

Krutrim Enterprise

AI Infrastructure

Indian large language model and cloud platform for enterprise AI workloads.

vLLM

AI Infrastructure

Open-source LLM serving framework with PagedAttention for high-throughput and memory-efficient inference.