10-12-2026, 10:32 AM
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: DeepSeek, TensorRT-LLM, 7900 XTX, with a lot of attention on KV cache pressure.
Feel free to tear it apart if you see something dumb.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Just sharing a setup that ended up working reasonably well: DeepSeek, TensorRT-LLM, 7900 XTX, with a lot of attention on KV cache pressure.
Feel free to tear it apart if you see something dumb.
For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
2x3090 • llama.cpp • too much VRAM is still not enough