Re:DeepSeek-V3 Technical Report
by danielhanchen on Thursday March 27, 2025 @06:05AM
(#43491932)
Re DeepSeek-V3 0324 - I made some 2.7bit dynamic quants (230GB in size) for those interested in running them locally via llama.cpp! Tutorial on getting and running them: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-...
[ Parent
| on HN ]
These articles are gold, thank you. I used your gemma one from a few weeks back to get gemma 3 performing properly. I know you guys are all GPU but do you do any testing on CPU/GPU mixes? I'd like to see the pp and t/s on pure 12 channel epyc and the same with using a 24 gig gpu to accelerate the pp.
Re:DeepSeek-V3 Technical Report
by danielhanchen on Thursday March 27, 2025 @06:10PM
(#43498772)
Oh fantastic! Oh for MoEs like DeepSeek, technically GPUs aren't that necessary! I actually tested on 1x H100 I think it was 30 layers offloaded, and the other 30 are on CPU - it wasn't that bad at all!