Search Results for "masmt runtime engine"

Torch-TensorRT is a compiler for PyTorch/TorchScript, targeting NVIDIA GPUs via NVIDIA’s TensorRT Deep Learning Optimizer and Runtime. Unlike PyTorch’s Just-In-Time (JIT) compiler, Torch-TensorRT is an Ahead-of-Time (AOT) compiler, meaning that before you deploy your TorchScript code, you go through an explicit compile step to convert a standard TorchScript program into a module targeting a TensorRT engine. Torch-TensorRT operates as a PyTorch extension and compiles modules that integrate into the JIT runtime seamlessly. ...

...The system supports multiple optimization techniques including quantization, pruning, and speculative decoding to improve performance while reducing computational overhead. It also provides tools to convert models from popular formats like PyTorch checkpoints into optimized runtime formats that can be executed on supported hardware platforms.

LiteRT is Google's next-generation on-device machine learning framework and the successor to TensorFlow Lite, designed for high-performance AI and generative AI deployment across edge devices. It provides efficient model conversion, optimization, and runtime execution while leveraging hardware acceleration from CPUs, GPUs, and NPUs. LiteRT supports a wide range of platforms, including Android, iOS, Linux, macOS, Windows, web environments, and IoT devices. The framework simplifies on-device...

Emscripten is a complete open-source compiler toolchain that transforms C, C++, and other LLVM-based source code into WebAssembly (and JavaScript), enabling native‑like applications to run in web browsers, Node.js, and other Wasm environments. While Emscripten mostly focuses on compiling C and C++ using Clang, it can be integrated with other LLVM-using compilers (for example, Rust has Emscripten integration, with the wasm32-unknown-emscripten and asmjs-unknown-emscripten targets). Emscripten...

CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many...

This project extends the Proximus development environment to support deployment of AI workloads on next-generation AMD Ryzen™ AI processors, such as the Ryzen™ AI 7 PRO 7840U featured in the Lenovo ThinkPad T14s Gen 4 ,one of the first true AI PCs with an onboard Neural Processing Unit (NPU) capable of 16 TOPS (trillion operations per second). Originally designed for use with Windows 11 Pro, this runtime was further enhanced to work under Linux environments, allowing developers and researchers to fully utilize the AMD AI Engine across both platforms. This cross-platform support is a major innovation, enabling AI workload portability, integration into CI environments, and deployment into Linux-based research and production pipelines.

Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux and Windows devices. Runtime is optimized with NEON, OpenCL and Hexagon, and Winograd algorithm is introduced to speed up convolution operations. The initialization is also optimized to be faster. Chip-dependent power options like big.LITTLE scheduling, Adreno GPU hints are included as advanced APIs.