+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: General (https://www.datasculpting.ai/inference/forumdisplay.php?fid=25)
+--- Thread: small win thread on A6000 (/showthread.php?tid=426)
small win thread on A6000 - rocmplane - 09-23-2026
Did a bit of testing and thought I'd post the result here.
Short version: TensorRT-LLM behaved well for me, but only after I stopped ignoring quant drift.
Happy to post more details if anyone wants them.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: small win thread on A6000 - cobalttinker - 09-24-2026
I'd approach it in a boring order. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: small win thread on A6000 - audioforge - 09-27-2026
I think the bottleneck is somewhere else. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere. 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: small win thread on A6000 - rocmplane - 09-27-2026
I'd start with the simpler stack.
Re: small win thread on A6000 - quiettoken - 09-27-2026
What worked for me was pretty simple. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: small win thread on A6000 - rocmplane - 09-27-2026
Thanks, that helps. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: small win thread on A6000 - rocmrunner40 - 09-27-2026
subscribed, curious where this lands.