this post was submitted on 31 Oct 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
Any tricks to speed up 13B models on a 3090? (alien.top)
submitted 1 year ago by DustGrouchy1792@alien.top to c/localllama@poweruser.forum
5 comments fedilink hide all child comments
 

Are there any tricks to speed up 13B models on a 3090?

Currently using the regular huggingface model quantized to 8bit by a GPTQ capable fork of KoboldAI.

Especially when the context limit changes, it's pretty slow and far from even remotely real time.

you are viewing a single comment's thread
view the rest of the comments
[–] AsliReddington@alien.top 1 points 1 year ago

Just run on TGI or vLLM for flash attention & continuous batching for parallel requests