latency vs throughput for small deployments on 7900 XTX

[kernelrunner]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

I'm happy to test one more variant if you want a second data point.

[cudaworks]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Once you know the plain pat

that fixed it for me too.