lxe

joined 1 year ago
sorted by: new top controversial old
ExLlamaV2: The Fastest Library to Run LLMs in c/localllama@poweruser.forum
[–] lxe@alien.top 1 points 11 months ago (1 children)

Agreed. Best performance running GPTQ’s. Missing the HF samplers but that’s ok.

When OpenAI takes neutering to the extreme... in c/localllama@poweruser.forum
[–] lxe@alien.top 1 points 11 months ago

So safe

So aligned

Executive order on AI - Now a good time to get my own local? in c/localllama@poweruser.forum
[–] lxe@alien.top 1 points 1 year ago

It’s an executive order about AI used by federal government.