Re:DeepSeek R1 analysis: open-source model has propaganda re...
by Anaphylaxis on Wednesday February 05, 2025 @08:08AM
(#42947958)
Sure but he explicitly stated, 'GPU Servers', making it likely he didn't use the CPU for inferencing, validating the question about what GPU setup did they use
Heard there are some optimizations for CPU inference on storage, then it should be somewhat a tad "less slow".
Time to split that RAM among your CPU cores and mmap blocks of weights for inference from storage.