1 个仓库
Awesome GitHub RepositoriesModel Method Initializations
The process of initializing specific execution paths, tensor metadata, and hardware delegates within a compiled model.
Distinct from Runtime Initializations: Focuses on AI model-specific method and delegate initialization rather than general language runtime setup.
Explore 1 awesome GitHub repository matching programming languages & runtimes · Model Method Initializations. Refine with filters or upvote what's useful.
Awesome Model Method Initializations 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。
- pytorch/executorch
pytorch/executorch
4,296在 GitHub 上查看ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,
Runs named methods on loaded models, passing tensors and retrieving outputs from the runtime.
Pythondeep-learningembeddedgpu
