10-13-2026, 03:02 PM
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Mistral, TensorRT-LLM, GB200, with a lot of attention on INT4.
Feel free to tear it apart if you see something dumb.
This is mostly for local work rather than public serving.
Just sharing a setup that ended up working reasonably well: Mistral, TensorRT-LLM, GB200, with a lot of attention on INT4.
Feel free to tear it apart if you see something dumb.
This is mostly for local work rather than public serving.