BentoML

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Community maintained hardware plugin for vLLM on Huawei Ascend

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.