10-19-2026, 04:06 AM
I don't think that's the whole story. I get why that seems right, but on Threadripper box the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
|
Help with Vector Databases for DeepSeek
|
|
10-19-2026, 04:06 AM
I don't think that's the whole story. I get why that seems right, but on Threadripper box the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
10-19-2026, 04:24 AM
I'd approach it in a boring order. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
10-19-2026, 04:43 AM
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
|
|
« Next Oldest | Next Newest »
|