10-07-2026, 05:44 PM
Did a bit of testing and thought I'd post the result here.
I tried this with Kimi using llama.cpp on 7900 XTX. The headline result was better than I expected, but prefix caching still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
I care more about stability than squeezing the last possible tokens/sec out of it.
I tried this with Kimi using llama.cpp on 7900 XTX. The headline result was better than I expected, but prefix caching still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
I care more about stability than squeezing the last possible tokens/sec out of it.
throughput matters, but tail latency matters too