10-04-2026, 01:55 AM
Did a bit of testing and thought I'd post the result here.
I tried this with Kimi using vLLM on GB200. The headline result was better than I expected, but VRAM headroom still ended up being the limiting factor.
Happy to post more details if anyone wants them.
I tried this with Kimi using vLLM on GB200. The headline result was better than I expected, but VRAM headroom still ended up being the limiting factor.
Happy to post more details if anyone wants them.
curious and caffeinated