Serverless GPU 3

Novita AI: AI cloud with model APIs, GPU instances, and serverless GPUs. Novita AI provides access to over 100 APIs, including AI image generation and editing with 10,000+ models, and training APIs for custom models. It offers cheap pay-as-you-go services, freeing users from GPU maintenance hassles while building their own products. Novita AI also provides GPU Instances and Serverless GPUs for scaling AI, optimizing performance, and innovating with ease and efficiency.

RightNow AI optimizes CUDA code and profiles kernels for peak GPU performance using AI. RightNow AI helps developers optimize their CUDA code and profile their kernels to spot bottlenecks and unlock peak GPU performance, getting the most out of their hardware. It automatically profiles, detects bottlenecks, and optimizes CUDA kernels for peak performance. It supports major NVIDIA architectures and allows generating optimized CUDA kernels instantly with AI.

Automated open-source AI model optimization and deployment API platform. RunInfra is an AI inference optimization and deployment platform that builds production-ready APIs from plain language descriptions of open-source models or full apps. Backed by Y Combinator, it benchmarks various serving engines (like vLLM, SGLang, and TensorRT-LLM) across different NVIDIA GPUs to find the most cost-effective and low-latency configuration. It leverages its automated Forge agent to optimize kernels, quantize models (AWQ, GPTQ, FP8), and handle continuous batching and KV cache tuning. Users can deploy on RunInfra's managed infrastructure with scale-to-zero capabilities or export the fully runnable deployment kit (Dockerfile, configs) to host on their own infrastructure like RunPod, Modal, or local hardware.