Apple unified memory limits: setup advice

[orbitline]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

[mellowstream]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice,

Can you fill in a bit more context? Is this local-only or are you routing anything externally?

[cudacrate]

[quote]I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous a

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[torchshed]

A couple questions before I guess too hard. Are you testing this on GB200 or something else?

[dockkite69]

That matches what I was seeing. The pattern around continuous batching has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[mellowstream]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

I'm happy to test one more variant if you want a second data point.