09-21-2026, 11:51 PM
Curious what people here are seeing.
My current setup is TensorRT-LLM with M3 Max, and I keep running into KV cache pressure.
If you've tested something similar, what did you keep and what did you stop bothering with?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
My current setup is TensorRT-LLM with M3 Max, and I keep running into KV cache pressure.
If you've tested something similar, what did you keep and what did you stop bothering with?
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
trying not to rebuild again