+- 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=671)
Pages:
1
2
small win thread on A6000 - quiettoken - 10-02-2026
Posting this in case it saves someone else a little time.
If you were starting from scratch today for this use case, what would you choose first and what would you ignore?
Simple and boring is a valid answer.
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 - edgequill - 10-03-2026
that fixed it for me too.
Re: small win thread on A6000 - ggufwire22 - 10-03-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: small win thread on A6000 - bytegarden73 - 10-05-2026
Interesting, I hadn't tried that. I ended up in about the same place using PyTorch. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: small win thread on A6000 - plaingarden18 - 10-05-2026
Thanks, that helps. The pattern around reranking has been pretty similar for me.
Re: small win thread on A6000 - ggufwire22 - 10-06-2026
that fixed it for me too. I keep promising myself this is the last rebuild.
Re: small win thread on A6000 - vectorshed43 - 10-06-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: small win thread on A6000 - sparrowghost - 10-06-2026
What worked for me was pretty simple. On mini PC, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
I'm happy to test one more variant if you want a second data point.
Re: small win thread on A6000 - localtinker - 10-06-2026
A couple things I'd check first. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: small win thread on A6000 - rocmrunner40 - 10-06-2026
That matches what I was seeing. 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.