LightLLM

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/ModelTC/LightLLM recorded 2026-08-31

  Repo metadata for ModelTC/LightLLM - archived false, 4,253 stars.

• https://raw.githubusercontent.com/ModelTC/LightLLM/main/LICENSE recorded 2026-10-07

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

• https://raw.githubusercontent.com/ModelTC/LightLLM/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.

GitHub stars are LightLLM's only adoption signal. A `lightllm` package exists on PyPI, but it publishes no repository link, so it could not be confirmed as this project's own and is not counted.

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

  Repo metadata - stargazers_count = 4,253 - for ModelTC/LightLLM.

LightLLM sits two tiers below vLLM, level with Text Generation Inference, which shares the same feature set: continuous batching, tensor parallelism, Flash Attention and quantization. It is placed there rather than higher because it assembles those techniques rather than publishing a serving record of its own.

• https://raw.githubusercontent.com/ModelTC/LightLLM/main/README.md recorded 2026-10-07

  README, read for the engine's feature set: Python-based serving with a lightweight design and horizontal scalability, assembled from FasterTransformer, TGI, vLLM and FlashAttention techniques.