1 个仓库
Awesome GitHub RepositoriesModel
Tools that translate trained model structures into executable source code for deployment.
Distinct from Code Generators: Specifically focuses on converting model parameters into hard-coded logic rather than general boilerplate generation
Explore 1 awesome GitHub repository matching software engineering & architecture · Model. Refine with filters or upvote what's useful.
Awesome Model GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- lightgbm-org/lightgbm
lightgbm-org/LightGBM
18,460在 GitHub 上查看LightGBM is a gradient boosting framework used to train decision tree ensembles for classification, regression, and ranking tasks. It functions as a distributed machine learning library and a decision tree ensemble implementation that utilizes leaf-wise growth and histogram-based feature binning. The framework is distinguished by its ability to offload heavy computations to CUDA or OpenCL devices for GPU acceleration and its capacity to parallelize training across multiple nodes using sockets, MPI, or Dask. It includes a specialized categorical feature processor that optimizes partitions for
Translates trained decision tree structures into C++ if-else statements for high-speed deployment.
C++
