transformers.js VS taichi.js

Thanks to transformers.js, we can run the tokenizer and model locally in the browser. Transformers.js is designed to be functionally equivalent to Hugging Face's transformers python library, meaning you can run the same pretrained models using a very similar API.

We have some other WebGPU demos, including:

- WebGPU embedding benchmark: https://huggingface.co/spaces/Xenova/webgpu-embedding-benchm...

- Real-time object detection: https://huggingface.co/spaces/Xenova/webgpu-video-object-det...

- Real-time background removal: https://huggingface.co/spaces/Xenova/webgpu-video-background...

- WebGPU depth estimation: https://huggingface.co/spaces/Xenova/webgpu-depth-anything

- Image background removal: https://huggingface.co/spaces/Xenova/remove-background-webgp...

You can follow the progress for full WebGPU support in the v3 development branch (https://github.com/xenova/transformers.js/pull/545).

To answer your question, while there are certain ops missing, the main limitation at the moment is for models with decoders... which are not very fast (yet) due to inefficient buffer reuse and many redundant copies between CPU and GPU. We're working closely with the ORT team to fix these issues though!

BTW: you might want to add support for typed arrays.

See: https://github.com/xenova/transformers.js/blob/8804c36591d11...

This is really old, but added as part of the shape of the vector as well: https://github.com/nicolaspanel/numjs/blob/master/src/dtypes...

Made possible by Xenova and Supabase / gte-small

To build the application, you’ll use the youtube-transcript package to retrieve YouTube video transcripts. You will then use LangChain and the Transformers.js package to generate free Hugging Face embeddings for the given transcript and store them in a vector store instead of relying on potentially expensive OpenAI embeddings. Lastly, you will use LangChain and an OpenAI model to retrieve information stored in the vector store.

Transformers.js: A groundbreaking library, Transformers.js brings transformer models like GPT-3, BERT, and Whisper straight to your browser. With the introduction of technologies like webGPU and LLM, Transformers.js has garnered significant attention. If you’d like to learn how to integrate a small model in the UI, check out their code and examples here.

The announcement seems somewhat disingenuous. The PR[1] found from their release notes[2] seems to contain only boilerplate and no real support for Mistral models or their weights.

[1]: https://github.com/xenova/transformers.js/pull/379

FWIW also taichi is quite popular in python and seems has some javascript related implementation (I haven't used it though), taichi.js [0]

[0] https://github.com/AmesingFlank/taichi.js

The independent compilation and execution leaves Taichi with more possibilities. Though embedded in Python, Taichi is not Python-specific. In fact, our community developer AmesingFlank is working on a Javascript frontend. You can check out some cool preliminary demos in the taichi.js github repo.

Taichi.js is a powerful project that adds a JS frontend to Taichi and compiles Taichi to WASM with Emscripten, allowing users to transform Javascript functions into WebGPU compute shaders for massive parallelization. If your browser supports WebGPU, you can try it out on Playground | taichi.js.