+- 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: batching changes after update (/showthread.php?tid=316)
Pages:
1
2
batching changes after update - audioriver - 09-17-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of PyTorch and M3 Max felt surprisingly usable once I tuned around prefill/decode split.
If someone wants the exact settings I can clean them up and post them.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Re: batching changes after update - amberkite - 09-18-2026
Ran a quick check on my box. On B200 with TensorRT-LLM, I saw basically the same behavior. I expected the model choice to matter more than it did. At this point the real bottleneck is my patience.
Re: batching changes after update - latentgarden - 09-18-2026
I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.
Re: batching changes after update - kernelmike - 09-21-2026
Interesting, I hadn't tried that. The pattern around workstation thermals has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: batching changes after update - amberpatch25 - 09-24-2026
I don't think that's the whole story. I've seen people blame tokens/sec when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.
Re: batching changes after update - cobaltspark - 09-24-2026
Good point. I ended up in about the same place using SGLang. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: batching changes after update - mangohouse - 09-24-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: batching changes after update - dockember - 09-24-2026
Appreciate the detail. I don't think your conclusion is far off.
Re: batching changes after update - orbitbench6 - 09-25-2026
worth checking the driver first.
Re: batching changes after update - latentgarden - 09-25-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.