Comment Comment by 1ba9115454 I'm running a Ryzen 7 8745HS with Radeon 780M (27GB RAM), using Ollama's Vulkan backend.I get ~45 tokens/s generation and ~680 tokens/s prompt processing.The problem is ollama is not caching the prompt, I get -> forcing full prompt re-processing due to lack of cache dataSo this wouldn't work in its current state in an agentic loop. parent 1ba9115454 17 days ago
I get ~45 tokens/s generation and ~680 tokens/s prompt processing.
The problem is ollama is not caching the prompt, I get -> forcing full prompt re-processing due to lack of cache data
So this wouldn't work in its current state in an agentic loop.