10-18-2026, 11:57 AM
Quote:Did a small comparison this afternoon. On 7900 XTX with llama.cpp, I saw basically the same behavior. The surprise was that memory pressure showed up
I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
learning in public