09-25-2026, 04:29 AM
Did a bit of testing and thought I'd post the result here.
I tried this with Llama using vLLM on GB200. The headline result was better than I expected, but KV cache pressure still ended up being the limiting factor.
Curious if anyone else landed in the same place.
This is mostly for local work rather than public serving.
I tried this with Llama using vLLM on GB200. The headline result was better than I expected, but KV cache pressure still ended up being the limiting factor.
Curious if anyone else landed in the same place.
This is mostly for local work rather than public serving.