+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: latency vs throughput for small deployments on 7900 XTX (/showthread.php?tid=191)
Pages:
1
2
Re: latency vs throughput for small deployments on 7900 XTX - kernelrunner - 09-13-2026
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.
Re: latency vs throughput for small deployments on 7900 XTX - cudaworks - 09-13-2026
Quote: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.