R1 (and K2) is MoE, whereas Llama 3 is a dense model family. MoE actually makes these models practical to run on cheaper hardware. DeepSeek R1 is more comfortable for me than Llama 3 70B for exactly that reason - if it spills out of the GPU, you take a large performance hit.
If you need to spill into CPU inference, you really want to be multiplying a different set of 32B weights for every token compared to the same 70B (or more) instead, simply because the computation takes so long.
IMHO it sets the local LLM community back when we lean on extreme quantization & streaming weights from disk to say something is possible*, because when people try it out, it turns out it's an awful experience.
* the implication being, anything is possible in that scenario
I will also point out that having three API-based providers deploying an impractically-large open-weights model beats the pants of having just one. Back in the day, this was called second-sourcing IIRC. With proprietary models, you're at the mercy of one corporation and their Kafkaesque ToS enforcement.
For GPU inference at scale, I think token-level batching is used.
For the big MLP tensors they would be split across GPUs in a cluster. Then for the MoE parts you would spread the experts across the GPUs and route to them based on which experts are active (there would likely be more than one if the batch size is > 1).
Given that R1 uses 37B active parameters (compared to 32B for K2), K2 should be slightly faster than that - around 1.15 tokens/second.
