09-13-2026, 12:06 AM
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of TensorRT-LLM and A6000 felt surprisingly usable once I tuned around prefill/decode split.
If someone wants the exact settings I can clean them up and post them.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.
This isn't revolutionary, but the combination of TensorRT-LLM and A6000 felt surprisingly usable once I tuned around prefill/decode split.
If someone wants the exact settings I can clean them up and post them.
My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.