+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Quality / Reliability Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=68)
+--- Thread: video model setup pain points with TensorRT-LLM (/showthread.php?tid=1120)
video model setup pain points with TensorRT-LLM - forgemixer - 10-12-2026
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.
I care more about stability than squeezing the last possible tokens/sec out of it. The logs were somehow calmer than I was.
Re: video model setup pain points with TensorRT-LLM - vramstream - 10-14-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost.
Re: video model setup pain points with TensorRT-LLM - batchwire - 10-14-2026
I tested this tonight. On mini PC with Ollama, I saw basically the same behavior.
Re: video model setup pain points with TensorRT-LLM - audioforge - 10-14-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
I'm happy to test one more variant if you want a second data point.
Re: video model setup pain points with TensorRT-LLM - quiethouse - 10-15-2026
Good point. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: video model setup pain points with TensorRT-LLM - batchsize - 10-15-2026
Quote:Good point. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt
My first guess would be this: 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.
I'm happy to test one more variant if you want a second data point.
Re: video model setup pain points with TensorRT-LLM - llmtrack - 10-15-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
Re: video model setup pain points with TensorRT-LLM - benchplease - 10-15-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.