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

Inferencing with AND X3D Processors (alien.top)

submitted 11 months ago by ccbadd@alien.top to c/localllama@poweruser.forum

6 comments fedilink hide all child comments

With the proof of concept done and users able to get over 180gb/s on a PC with AMD's 3d vcache, it sure would be nice if we could figure a way to use that bandwidth for CPU based inferencing. I think it only worked on Windows but if that is the case we should be able to come up with a way to do it under Linux too.

you are viewing a single comment's thread
view the rest of the comments

[–] tu9jn@alien.top 1 points 11 months ago (1 children)

Vcache only helps when you want to access lots of tiny chunks of data that fit inside the 96-128mb cache.

During inference you have to read the entire several Gb model for each token generation, so your botleneck is still the Ram bandwidth.

[–] ccbadd@alien.top 1 points 11 months ago

In the article they said that that is what was expected but the gains impacted the entire ramdrive and the concept has been proven now. The test used a 500mb+ block so bigger than the cache alone.

https://www.tomshardware.com/news/amd-3d-v-cache-ram-disk-182-gbs-12x-faster-pcie-5-ssd