video model setup pain points with TensorRT-LLM

[forgemixer]

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.

[vramstream]

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.

[batchwire]

I tested this tonight. On mini PC with Ollama, I saw basically the same behavior.

[audioforge]

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.

[quiethouse]

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.

[batchsize]

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.

[llmtrack]

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.

[benchplease]

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.