https://raw.githubusercontent.com/OrcVole/vllm-cloudron/main/CloudronVersions.json
Description
0.30.0
vLLM is a high-throughput inference server for large language models with the most widely
supported OpenAI-compatible API of the self-hosted options. This package runs it as a
Cloudron app: one install serves one model at https://<location>/v1, protected by a
generated API key, with weights cached locally and every OpenAI-style client able to connect
unchanged.
This is CPU inference (amd64). It will not match GPU speed and it is not meant to: it gives integrations, automations and privacy-sensitive workloads a fully self-hosted OpenAI endpoint on the server you already run. Pair it with a chat frontend, an AI gateway, embeddings and a vector store to complete a private AI stack on Cloudron.
Unofficial community package. Not affiliated with the vLLM project or Cloudron.
Recent Changes
Update vLLM 0.29.0 to 0.30.0
New models: DeepSeek-V4.1-Flash, GLM-5.3-Flash, K2-Horizon; Fast Start weight-cache daemon
Watermarking support and HiSparse tiering improvements
Scale-out endpoints now opt-in via
--enable-scale-outflag (env var removed upstream)Packaging: no changes required for this Cloudron package
Base image cloudron/base 5.0.0 to 5.1.0: the Ubuntu 24.04.4 point release, with its OS security
updates. Same Ubuntu 24.04 release and glibc 2.39.