ZML

license

Apache-2.0(OSI)

source

public(the published repository is the engine)

core-gated

ungated(no enterprise path in the repository root and no paid build of the engine in the README)

The LICENSE body is the Apache-2.0 text with the APPENDIX omitted and no appended condition, read in full rather than taken from the API's label. The repository is public and unarchived and builds the engine itself. Its root tree carries no enterprise, ee or commercial directory and its README describes no licence-gated build, so the core reads as ungated. Confidence is medium because that is a repository-and-README read rather than a pricing-page read.

• https://raw.githubusercontent.com/zml/zml/master/LICENSE recorded 2026-08-31

  LICENSE body, read in full: the Apache-2.0 text with the APPENDIX omitted and no appended condition.

• https://api.github.com/repos/zml/zml recorded 2026-08-31

  Repo metadata for zml/zml - archived false, 4,011 stars.

• https://raw.githubusercontent.com/zml/zml/master/README.md recorded 2026-08-31

  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.

4,011 GitHub stars, in the 1K-10K band of the stars scale. The `zml` package on PyPI is an unrelated project called zero markup language, so no package artifact is declared and stars are the only instrument available.

• https://api.github.com/repos/zml/zml recorded 2026-08-31

  Repo metadata - stargazers_count = 4,011 - for zml/zml.

One band below the vllm anchor. Its hardware reach is broader than most engines here, but it compiles and executes models rather than providing the batching, paged-attention and OpenAI-compatible serving surface the anchor is banded on.

• https://raw.githubusercontent.com/zml/zml/master/README.md recorded 2026-08-31

  README, read for the engine's feature set: Ahead-of-time compilation of a model to a target accelerator across NVIDIA, AMD, Intel, TPU and Trainium, from one stack.