best sandbox for trying risky tools

[promptfield]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[sparrowkite53]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher.

[vrambandit]

A couple things I'd check first. 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.

[batchpeak]

A couple things I'd check first. If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glam

What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Once you know the plain path works, then add the faster path back in piece by piece. At this point the real bottleneck is my patience.

[sparrowcraft]

I think the bottleneck is somewhere else. I get why that seems right, but on GB200 the bottleneck felt elsewhere.