The gain is only in prefill and if the task/output is complex the gain will be totally minor. So the numbers are quitly exagerated here based on a prompt that is taking less than 2s to decode. So I guess we are not here doing complex tasks with 100's or 1000 token output.
For the cost of an M3 Ultra + DGX the gain seem minimal and most of all, exo didn't clarify the model used here and it's for sure not a dense model or an MoE with 1B or 2B experts otherwise the mac ultra too will suffer a lot and the layers will be bigger!
I'm confused by all the takes implying decode is more important than prefill.
There are an enormous number of use cases where the prompt is large and the expected output is small.
E.g. providing data for the LLM to analyze, after which it gives a simple yes/no Boolean response. Or selecting a single enum value from a set.
This pattern seems far more valuable in practice, than the common and lazy open ended chat style implementations (lazy from a product perspective).
Obviously decode will be important for code generation or search, but that's such a small set of possible applications, and you'll probably always do better being on the latest models in the cloud.
This is a wonderful explanation of the two phases! I appreciate the hardware concerns for both now.
Reading the article I wished for a device that just does both things well and on that topic it might be noteworthy that Apple's just-released M5 has approximately 3.5x-ed TTFT performance compared to M4, according to their claims!
10 comments
[ 6.4 ms ] story [ 34.8 ms ] threadThere are an enormous number of use cases where the prompt is large and the expected output is small.
E.g. providing data for the LLM to analyze, after which it gives a simple yes/no Boolean response. Or selecting a single enum value from a set.
This pattern seems far more valuable in practice, than the common and lazy open ended chat style implementations (lazy from a product perspective).
Obviously decode will be important for code generation or search, but that's such a small set of possible applications, and you'll probably always do better being on the latest models in the cloud.
Now I'm trying to stop myself from finding an excuse to spend upwards of $30k on compute hardware...
Reading the article I wished for a device that just does both things well and on that topic it might be noteworthy that Apple's just-released M5 has approximately 3.5x-ed TTFT performance compared to M4, according to their claims!