LM Studio

OpenRouter is a unified interface for LLMs. OpenRouter scouts for the lowest prices and best latencies/throughputs across dozens of providers, and lets you choose how to prioritize them. No need to change your code when switching between models or providers. You can even let users choose and pay for their own. Evals are flawed; instead, compare models by how often they're used for different purposes. Chat with multiple at once in the chatroom. Model usage can be paid by users, developers, or both, and may shift in availability. You can also fetch models, prices, and limits via API. OpenRouter routes requests to the best available providers for your model, given your preferences. By default, requests are load-balanced across the top providers to maximize uptime, but you can customize how this works using the provider object in the request body. Prioritize providers that have not seen significant outages in the last 10 seconds.

VLLM is a high-performance library designed to facilitate efficient inference and serving of Large Language Models (LLMs). Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. It offers state-of-the-art serving throughput by efficiently managing attention key and value memory through its PagedAttention mechanism. It supports continuous batching of incoming requests and utilizes optimized CUDA kernels, including integration with FlashAttention and FlashInfer, to enhance model execution speed. Additionally, vLLM provides quantization support for GPTQ, AWQ, INT4, INT8, and FP8, as well as speculative decoding capabilities. Users benefit from seamless integration with popular Hugging Face models, support for various decoding algorithms such as parallel sampling and beam search, and compatibility with NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs, and more.