+- 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 with TensorRT-LLM (/showthread.php?tid=105)
TensorRT-LLM worth the setup time with TensorRT-LLM - syshouse - 09-03-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on 7900 XTX, I ended up with decent performance, but the setup only really made sense once I adjusted around consumer GPUs.
Curious if anyone else landed in the same place.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - syshouse - 09-04-2026
that fixed it for me too.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - vectorport - 09-06-2026
Good point. The pattern around structured output 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: TensorRT-LLM worth the setup time with TensorRT-LLM - rasterbench - 09-06-2026
Quote:Good point. The pattern around structured output has been pretty similar for me. I got better results once I stopped chasing one metric and just looke
I'd approach it in a boring order. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - syshouse - 09-06-2026
Quote:[quote]Good point. The pattern around structured output has been pretty similar for me. I got better results once I stopped chasing one metric and jus
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - batchcraft - 09-06-2026
I hit almost the same issue last night.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - plainscope50 - 09-06-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
I'm happy to test one more variant if you want a second data point.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - vectorshed43 - 09-07-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - kernelpeak - 09-07-2026
Quote:Can you fill in a bit more context? What model, what runtime, and roughly what context size?
I tested this tonight. On A6000 with vLLM, I saw basically the same behavior.
Re: TensorRT-LLM worth the setup time with TensorRT-LLM - batchcraft - 09-07-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.