+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: TensorRT-LLM (https://www.datasculpting.ai/inference/forumdisplay.php?fid=37)
+--- Thread: serving on Blackwell (/showthread.php?tid=1354)
Pages:
1
2
Re: serving on Blackwell - kernelmike - 10-19-2026
What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: serving on Blackwell - rasterbench - 10-19-2026
Maybe, but I had the opposite result. I've seen people blame batch size when the real issue was much more mundane.
Re: serving on Blackwell - tensorfield88 - 10-19-2026
Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there.
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at prefix caching.