+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: NVIDIA / CUDA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=31)
+--- Thread: Blackwell deployment chatter on Threadripper box (/showthread.php?tid=1365)
Pages:
1
2
Re: Blackwell deployment chatter on Threadripper box - kernelmike - 10-19-2026
worth checking the driver first.
Re: Blackwell deployment chatter on Threadripper box - phaseport36 - 10-19-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: Blackwell deployment chatter on Threadripper box - amberpatch25 - 10-19-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
Re: Blackwell deployment chatter on Threadripper box - audioriver - 10-19-2026
I hit almost the same issue last night.
Re: Blackwell deployment chatter on Threadripper box - latentgarden - 10-19-2026
I tested this tonight. On 7900 XTX with llama.cpp, I saw basically the same behavior. I expected the model choice to matter more than it did.
Re: Blackwell deployment chatter on Threadripper box - orbitbench6 - 10-19-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.