+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: NVIDIA / CUDA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=31)
+--- Thread: Blackwell deployment chatter on A6000 (/showthread.php?tid=1221)
Blackwell deployment chatter on A6000 - southpatch - 10-15-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of MLX and B200 felt surprisingly usable once I tuned around prefill/decode split.
Maybe useful as a starting point for newer folks.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: Blackwell deployment chatter on A6000 - routecrate - 10-16-2026
What worked for me was pretty simple. If you're on TensorRT-LLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: Blackwell deployment chatter on A6000 - thetapath - 10-16-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: Blackwell deployment chatter on A6000 - edgecoast - 10-17-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: Blackwell deployment chatter on A6000 - cobaltspark - 10-17-2026
Quote:Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, no
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at NVFP4. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: Blackwell deployment chatter on A6000 - latentgarden - 10-17-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.
Re: Blackwell deployment chatter on A6000 - amberpatch25 - 10-19-2026
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.