FastDeploy
PaddlePaddleFastDeploy is an inference and deployment toolkit for large language models and vision language models built on PaddlePaddle, shipping out-of-the-box deployment paths for production serving.
The `fastdeploy-python` package on PyPI resolves to this repository but drew 323 downloads in the trailing 30 days, so it measures a minority channel and is not declared.
Openness
5 medium confidence- 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
The LICENSE body is the unmodified Apache-2.0 text. The repository is public, active and builds the engine itself, with no enterprise or paid tier in the root tree or README.
- https://api.github.com/repos/PaddlePaddle/FastDeploy recorded 2026-08-31
Repo metadata for PaddlePaddle/FastDeploy - archived false, 3,711 stars.
- https://raw.githubusercontent.com/PaddlePaddle/FastDeploy/develop/LICENSE recorded 2026-10-07
LICENSE body, read in full: the stock Apache-2.0 text with a PaddlePaddle Authors copyright line prepended, which is a notice rather than an added term.
- https://raw.githubusercontent.com/PaddlePaddle/FastDeploy/develop/README_EN.md recorded 2026-10-07
English README, the file README.md links to: an inference and deployment toolkit for LLMs and VLMs on PaddlePaddle, with per-hardware installation guides and no paid tier, enterprise edition or license-gated build beside the published source.
Adoption
2 low confidenceFastDeploy has no declared package artifact, so GitHub stars are the only adoption signal available. A star is not a use, so this reading is a floor on adoption rather than a full account of it.
- https://api.github.com/repos/PaddlePaddle/FastDeploy recorded 2026-08-31
Repo metadata - stargazers_count = 3,711 - for PaddlePaddle/FastDeploy.
Capability
4 medium confidenceFastDeploy sits a tier below vLLM. It serves both language and vision-language models, but within the PaddlePaddle ecosystem rather than across the broader model and hardware range vLLM covers.
- https://raw.githubusercontent.com/PaddlePaddle/FastDeploy/develop/README_EN.md recorded 2026-10-07
README "About": "an inference and deployment toolkit for large language models and visual language models based on PaddlePaddle", with load-balanced PD disaggregation, KV cache transfer over NVLink/RDMA, a vLLM-compatible OpenAI API server and multi-hardware support.
Verified 2026-09-27