web-llm

web-llm copied to clipboard

Initialize GPU device: WebGPU - Intel(R) UHD Graphics 630

5

I have successfully run on my macOS, but the GPU is using Intel, which is too slow. My macOS is equipped with an 8G AMD graphics card, how can I...

ZhouXiaolin

hugging face -> Hugging Face

eltociear

Can you write a tutorial for local deployment?

37

Can you write a tutorial for local deployment?

zsodur

I get Generate error, Error: WebGPU: cannot factorize big gridDim.x=104197 when I paste text into the box sometimes.

1

On an M1 Macbook Pro with 16GB running OS 13.1

itissid

So I have been following the AI boom that's started the past 1-2 months. I am personally very interested in decentralizing AI models and access. My project (https://lumeweb.com) is in...

pcfreak30

Thank you very much for this open source project, which allows ordinary computers to use LLM I hope to be able to call web llm through API in my own...

howie6879

Does not work for me on Windows 11 and Chrome Canary

1

Chrome Version 114.0.5715.0 (Official Build) canary (64-bit) The error is: mlc.ai/:1 No available adapters. llm_chat.js:421 Error: Cannot find adapter that matches the request at Object. (tvmjs.bundle.js:587:24) at Generator.next () at...

kohlerm

[WIP] Support Dolly

3

junrushao

Sorry I am submitting this here, I am just wondering how can I run llama using chroma-beta in headless mode?

qaiwiz

[BUG] Find an error initializing the WebGPU device OperationError: D3D12

9

While running on the candy chrome I got those errors: (firstly the `Init error` and on the second request the rest) ``` [System Initalize] Initialize GPU device: WebGPU - intel...

0dminnimda