← Back to context Comment by p12tic 2 months ago All of this is for batch size 1. 2 comments p12tic Reply qeternity 2 months ago I know. That was my point.Throughput doesn't scale on CPU as well as it does on GPU. p12tic 2 months ago We both agree. Batch size 1 is only relevant to people who want to run models on their own private machines. Which is the case of OP.
qeternity 2 months ago I know. That was my point.Throughput doesn't scale on CPU as well as it does on GPU. p12tic 2 months ago We both agree. Batch size 1 is only relevant to people who want to run models on their own private machines. Which is the case of OP.
p12tic 2 months ago We both agree. Batch size 1 is only relevant to people who want to run models on their own private machines. Which is the case of OP.
I know. That was my point.
Throughput doesn't scale on CPU as well as it does on GPU.
We both agree. Batch size 1 is only relevant to people who want to run models on their own private machines. Which is the case of OP.