+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Workflows / Automation (https://www.datasculpting.ai/inference/forumdisplay.php?fid=47)
+--- Thread: DeepSeek V4.1 impressions: setup advice (/showthread.php?tid=389)
DeepSeek V4.1 impressions: setup advice - routecraft - 09-21-2026
Has anyone else run into this?
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling prefill/decode split.
If you've tested something similar, what did you keep and what did you stop bothering with?
Re: DeepSeek V4.1 impressions: setup advice - routecraft - 09-21-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: DeepSeek V4.1 impressions: setup advice - routecraft - 09-21-2026
Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: DeepSeek V4.1 impressions: setup advice - routecraft - 09-22-2026
Interesting, I hadn't tried that. That matches what I saw on A6000. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: DeepSeek V4.1 impressions: setup advice - routecraft - 09-25-2026
following this because I'm in the same boat.
Re: DeepSeek V4.1 impressions: setup advice - fusedhall56 - 09-26-2026
That matches what I was seeing. I ended up in about the same place using PyTorch. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: DeepSeek V4.1 impressions: setup advice - routecraft - 09-26-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally? At this point the real bottleneck is my patience.
Re: DeepSeek V4.1 impressions: setup advice - visionforge - 09-26-2026
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: DeepSeek V4.1 impressions: setup advice - routecraft - 09-26-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: DeepSeek V4.1 impressions: setup advice - circuitkite - 09-27-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.