ngxson / wllama

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
https://huggingface.co/spaces/ngxson/wllama
MIT License
444 stars 23 forks source link

[Idea] Load model from File Blob #42

Closed ngxson closed 5 months ago

ngxson commented 6 months ago

With the introduction of heapfs, we can now do more low-level things.

The idea is to load File Blob directly into wllama's heap without creating any intermediate buffer.

This will ultimately allow us to use OPFS as mentioned in #38