ONNXRuntime Node.js binding
This repository provides native TensorFlow execution in backend JavaScript applications under the Node.js runtime, accelerated by the TensorFlow C binary under the hood. It provides the same API as [TensorFlow.js](https://js.tensorflow.org/api/latest/).
Extension of @node-llama-cpp/linux-x64-cuda - prebuilt binary for node-llama-cpp for Linux x64 with CUDA support
Classify GPU's based on their benchmark score in order to provide an adaptive experience.
Whisper.cpp Node.js binding with auto model offloading strategy.
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
The luma.gl core Device API
An another Node binding of whisper.cpp to make same API with whisper.rn as much as possible.
Lightweight debugging utility for Node.js and the browser
Extension of @node-llama-cpp/win-x64-cuda - prebuilt binary for node-llama-cpp for Windows x64 with CUDA support
[](https://www.npmjs.com/package/stats-gl) [](https://www.npmjs.com/package/st
KTX 2.0 (.ktx2) parser and serializer.
Prebuilt binary for node-llama-cpp for Linux x64 with CUDA support
An another Node binding of llama.cpp
TypeScript definitions for debug
Drop-in replacement for onnxruntime-node with DirectML and Cuda support
Source maps support for istanbul
Chunk package for the Linux x64 CUDA fallback backend used by node-llama-cpp (1/6)
Chunk package for the Windows x64 CUDA fallback backend used by node-llama-cpp (5/6)
This package is intended for Prisma's internal use
Chunk package for the Windows x64 CUDA fallback backend used by node-llama-cpp (1/6)
CUDA grammar for tree-sitter
Opt-in GPU debug instrumentation for tracked memory, dispatch, queue, and frame-budget metrics in Plasius WebGPU runtimes.
Extension of @realtimex/linux-x64-cuda - prebuilt binary for node-llama-cpp for Linux x64 with CUDA support
CUDA FFI bridge and kernel dispatch for dsfb-gpu-debug. Builds without nvcc unless the `cuda` feature is set.
CLI binary for dsfb-gpu-debug: generate fixtures, run CPU/GPU pipelines, compare case files.
Atlas detector algebra + S1.2 registry generator for DSFB-GPU-Atlas (162-spec literature-bound registry; registry_hash_v2 over the T.10-frozen corpus; no GPU coupling).
Literature detector corpus and canonicalisation court for DSFB-GPU-Atlas.
Deterministic CPU reference, hash chain, and semantic authority for dsfb-gpu-debug.