JSPM

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Native module for An another Node binding of llama.cpp (win32-x64-cuda)

Native module for An another Node binding of whisper.cpp (win32-x64-vulkan)

Native module for An another Node binding of whisper.cpp (linux-x64-cuda)

Native module for An another Node binding of whisper.cpp (win32-arm64)

Native module for An another Node binding of whisper.cpp (linux-x64)

Native module for An another Node binding of whisper.cpp (win32-x64)

An another Node binding of whisper.cpp to make same API with whisper.rn as much as possible.

Native module for An another Node binding of whisper.cpp (linux-x64-vulkan)

Native module for An another Node binding of whisper.cpp (linux-arm64-vulkan)

Native module for An another Node binding of whisper.cpp (linux-arm64-cuda)

Native module for An another Node binding of whisper.cpp (win32-x64-cuda)

Native module for An another Node binding of whisper.cpp (linux-arm64)

Native module for An another Node binding of whisper.cpp (win32-arm64-vulkan)

Native module for An another Node binding of whisper.cpp (darwin-arm64)

Native module for An another Node binding of whisper.cpp (darwin-x64)

CUDA bindings for Node.js

High-performance HLS transcoding library with hardware acceleration, intelligent client management, and distributed processing support for Node.js

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

CLI for nvGraph, which is a GPU-based graph analytics library written by NVIDIA, using CUDA.

High-performance CUDA to WebAssembly/WebGPU transpiler with Rust safety - Run GPU kernels in browsers and Node.js

Run AI models locally on your machine with node.js bindings for llama.cpp. Force a JSON schema on the model output on the generation level

Node.js client for Vast.ai API - Rent GPUs for machine learning and AI workloads

Run AI models locally on your machine with node.js bindings for llama.cpp. Force a JSON schema on the model output on the generation level

Cuda Node JS binding using napi API with working example.

`node-nvrtc`是一个简易的使用`nvrtc`的`node.js`扩展，目前只包含简单的`nvrtc`功能和`cuda`内存交换相关功能。

A mininal binding to bind generics.js with tensorflow to use GPU / CUDA.

Aho-Corasick string matching algorithm implementation with GPU acceleration using CUDA