+- 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: what are you seeing? (/showthread.php?tid=765)
Pages:
1
2
Re: serving on Blackwell: what are you seeing? - routecrate - 10-10-2026
A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: serving on Blackwell: what are you seeing? - macrotinker - 10-10-2026
I hit almost the same issue last night.
I'm happy to test one more variant if you want a second data point.
Re: serving on Blackwell: what are you seeing? - routecrate - 10-10-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: serving on Blackwell: what are you seeing? - cobaltlab - 10-10-2026
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Re: serving on Blackwell: what are you seeing? - batchcraft - 10-13-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: serving on Blackwell: what are you seeing? - kernelgrid - 10-13-2026
I hit almost the same issue last night.