RTP-LLM

license

Apache-2.0(OSI)

source

public(the published repository is the engine)

core features withheld

no — no enterprise path in the repository root and no paid build of the engine in the README

RTP-LLM's LICENSE is the Apache-2.0 text with no appended condition, and the public repository is the engine itself rather than a wrapper around closed code. Its root carries no enterprise or commercial directory, and the README describes no license-gated build, so nothing in the published source is held back.

• https://api.github.com/repos/alibaba/rtp-llm recorded 2026-08-31

  Repo metadata for alibaba/rtp-llm - archived false, 1,321 stars.

• https://raw.githubusercontent.com/alibaba/rtp-llm/main/LICENSE recorded 2026-10-07

  LICENSE body, read in full: the stock Apache-2.0 text with the copyright placeholder unfilled and no appended condition.

• https://raw.githubusercontent.com/alibaba/rtp-llm/main/README.md recorded 2026-10-07

  README, read for a paid tier, an enterprise edition or a licence-gated build beside the published source, and for whether any component is stated to be private.

No package artifact is declared for RTP-LLM, so GitHub stars are the only adoption signal available. The count should be read as a floor rather than a full measure of use.

• https://api.github.com/repos/alibaba/rtp-llm recorded 2026-08-31

  Repo metadata - stargazers_count = 1,321 - for alibaba/rtp-llm.

RTP-LLM sits one tier below vLLM. It accelerates inference the same way vLLM does, but over a narrower published surface: it documents no multi-node serving record and no OpenAI-compatible API server.

• https://raw.githubusercontent.com/alibaba/rtp-llm/main/README.md recorded 2026-10-07

  README, read for the engine's feature set: LLM inference acceleration, derived from FasterTransformer and maintained for Alibaba's own serving.