Chen Chiu

icon company Red Hat icon location United States icon location I'm Chen AKA LIMITLESS. My views are solely my own and do not reflect those of any other person or organization.

Results 9 comments of Chen Chiu

Decouple LLM Interface Code for Improved Scalability

> This is a good point and I also noticed this. I did some refactoring in #1008. Could you take a look and review it? I am not sure whether...

when will add the stream feature in api？

I need this as well!

when will add the stream feature in api？

I was looking into this and to make this work there has to be to adjustment the api server to accept a parameter "stream". `JSON CURL` ``` { "model": "vicuna-13b",...

when will add the stream feature in api？

@baradm100 where's your tip jar?

when will add the stream feature in api？

@merrymercy @baradm100 Hey, I was able to test this. I was able to get delta token updates on my responses. However, there is some wiredness with the api working with...

Cmake file always assumes AVX2 support

This issue is causing an issue downstream on "llama-cpp-python" where we cant build a python binding on non supported AVX2 machines that require cuBLAS support. Please read my workaround on...

Client return "H" on video...

Same Here, Cant seem to find a fix it either :( I've noticed that when the targeted DIR on the client side is WIPED it removes the returned "H". Client.php...

A lite version of the DAN 11.0 Prompt

https://shareg.pt/E06vGq1

[BUG] Black Screen with GPU + KDE

I was able to work around this issue by doing a `podman exec -it bash` and manually executing the startwm.sh script inside `/defaults` Another way I was able to work...