+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: Systems & Builds (https://www.datasculpting.ai/inference/forumdisplay.php?fid=29)
+--- Thread: Threadripper build for inference (/showthread.php?tid=262)
Pages:
1
2
Threadripper build for inference - homelabhenry - 09-13-2026
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.
Re: Threadripper build for inference - batchyard - 09-14-2026
Quote:Posting this in case it saves someone else a little time.
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Threadripper build for inference - tensorworks - 09-14-2026
Quote:Quote:Posting this in case it saves someone else a little time.
My first guess would be this: On 5090, 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. Turns out 'just one more test' was a lie.
Re: Threadripper build for inference - edgequill - 09-14-2026
Quote:Quote:Quote:Posting this in case it saves someone else a little time.
I'd approach it in a boring order. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: Threadripper build for inference - labnest - 09-14-2026
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.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: Threadripper build for inference - rocmmixer - 09-14-2026
I hit almost the same issue last night.
Re: Threadripper build for inference - latentpeak22 - 09-15-2026
Appreciate the detail. I don't think your conclusion is far off.
Re: Threadripper build for inference - sanevault - 09-15-2026
What worked for me was pretty simple. On 4090, 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.
Re: Threadripper build for inference - phasenode - 09-15-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there.
Re: Threadripper build for inference - sanevault - 09-15-2026
Tried to reproduce it just now. On B200 with MLX, I saw basically the same behavior. The main thing that moved was latency, not quality.