benchmark
opov
benchmark | opov | |
---|---|---|
3 | 1 | |
789 | 11 | |
3.3% | - | |
9.8 | 3.3 | |
7 days ago | about 1 year ago | |
Python | JavaScript | |
BSD 3-clause "New" or "Revised" License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
benchmark
-
PyTorch Primitives in WebGPU for the Browser
>What's a fair benchmark?
the absolute golden benchmarks are https://github.com/pytorch/benchmark
- [R] AMD Instinct MI25 | Machine Learning Setup on the Cheap!
-
[R] PyTorch | Budget GPU Benchmarking
TorchBench (https://github.com/pytorch/benchmark) is used by PyTorch core developers to test performance across a wide variety of models. I've never used it personally though.
opov
-
PyTorch Primitives in WebGPU for the Browser
I got nerdsniped and made a small library to test this concept. Might maintain
https://github.com/crubier/opov
What are some alternatives?
llama.cpp - LLM inference in C/C++
requests-wasm-polyfill - Drop-in replacement for the requests library for wasm python
wonnx - A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web
potatogpt - Pure Typescript, dependency free, ridiculously slow implementation of GPT2 for educational purposes
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
shumai - Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
tfjs - A WebGL accelerated JavaScript library for training and deploying ML models.