+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: TensorRT-LLM (https://www.datasculpting.ai/inference/forumdisplay.php?fid=37)
+--- Thread: TensorRT-LLM worth the setup time: early impressions (/showthread.php?tid=730)
TensorRT-LLM worth the setup time: early impressions - kernelmike - 10-04-2026
I'm trying to sanity-check my setup.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling HBM constraints.
Not looking for the perfect answer, mostly what worked in real use.
Re: TensorRT-LLM worth the setup time: early impressions - kernelmike - 10-06-2026
That matches what I was seeing. I ended up in about the same place using SGLang. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: TensorRT-LLM worth the setup time: early impressions - northcraft90 - 10-06-2026
Thanks, that helps. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: TensorRT-LLM worth the setup time: early impressions - cudapeak - 10-07-2026
Quote:Thanks, that helps. That matches what I saw on B200. I got better results once I stopped chasing one metric and just looked at whether the workflow fe
My first guess would be this: If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: TensorRT-LLM worth the setup time: early impressions - torchtrack24 - 10-08-2026
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.
Re: TensorRT-LLM worth the setup time: early impressions - batchsize - 10-08-2026
Quote: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.
following this because I'm in the same boat.
Re: TensorRT-LLM worth the setup time: early impressions - kernelmike - 10-09-2026
Interesting, I hadn't tried that. 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: TensorRT-LLM worth the setup time: early impressions - rasterbench - 10-10-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: TensorRT-LLM worth the setup time: early impressions - northcraft90 - 10-13-2026
Quote:Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at workstation thermals. Once you know the plain path works, then add the faster path back in piece by piece.
Re: TensorRT-LLM worth the setup time: early impressions - routecrate - 10-13-2026
I hit almost the same issue last night.