praeclarum / webgpu-torchLinks
Tensor computation with WebGPU acceleration
☆634Updated last year
Alternatives and similar repositories for webgpu-torch
Users that are interested in webgpu-torch are comparing it to the libraries listed below
Sorting:
- Modern GPU Compute and Rendering in Javascript☆519Updated last year
- Fast matrix-matrix multiplication on web browser using WebGPU☆127Updated last year
- 🧠 Web Neural Network API☆470Updated 2 weeks ago
- wander - the Wasm Renderer☆764Updated 8 months ago
- Tensor library for machine learning☆273Updated 2 years ago
- Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight☆1,163Updated last year
- Online compiler for HIP and NVIDIA® CUDA® code to WebGPU☆198Updated 10 months ago
- A cross-platform browser ML framework.☆721Updated 11 months ago
- WebGPU LLM inference tuned by hand☆150Updated 2 years ago
- Run modern deep learning models in the browser.☆845Updated last year
- Web-optimized vector database (written in Rust).☆258Updated 8 months ago
- 🕸️🦀 A WASM vector similarity search written in Rust☆1,007Updated 2 years ago
- Code samples for 'WebGPU Unleashed: A Practical Tutorial'☆324Updated last year
- ☆1,278Updated 2 years ago
- A browser-based, WebGL2 implementation of GPT-2 with transform block and attention matrix visualization☆342Updated 3 weeks ago
- Fast WebGPU 3d math library☆416Updated 5 months ago
- WebAssembly binding for llama.cpp - Enabling on-browser LLM inference☆939Updated last month
- SwissGL is a minimalistic wrapper on top of WebGL2 JS API. It's designed to reduce the amount of boilerplate code required to manage GLSL…☆1,220Updated 4 months ago
- JS tokenizer for LLaMA 1 and 2☆361Updated last year
- 🧠✨ Web Neural Network API samples☆157Updated last week
- ☆872Updated this week
- Inference Llama 2 in one file of pure JavaScript(HTML)☆34Updated 5 months ago
- Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.☆3,694Updated last year
- jsgrad is a dependency-free ML library in Typescript for model inference and training with support to WebGPU and other runtimes.☆59Updated 6 months ago
- LLM-based code completion engine☆190Updated 9 months ago
- Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)☆568Updated 2 years ago
- C++ implementation for BLOOM☆806Updated 2 years ago
- A JavaScript library like PyTorch, with GPU acceleration.☆1,209Updated last year
- FlashAttention (Metal Port)☆554Updated last year
- ☆248Updated last year