BerriAI/litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

⭐ 36902 | 🍴 5981

NVIDIA/nvidia-docker

Build and run Docker containers leveraging NVIDIA GPUs

⭐ 17500 | 🍴 2047

NVIDIA/open-gpu-kernel-modules

NVIDIA Linux open GPU kernel module source

⭐ 16734 | 🍴 1594

vosen/ZLUDA

CUDA on non-NVIDIA GPUs

⭐ 13962 | 🍴 898