DeepSeek V4.1 impressions for Llama

[quantghost]

that fixed it for me too.

I'd start with the simpler stack.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.

[routecraft]

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

[oxideworks59]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[signalcraft14]

that fixed it for me too.

[quantshed]

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints.

[routecraft]

that fixed it for me too.

subscribed, curious where this lands.