+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: prefill bottlenecks on longer prompts on A6000 (/showthread.php?tid=916)
Pages:
1
2
Re: prefill bottlenecks on longer prompts on A6000 - batchpeak - 10-13-2026
Quote:I tested this tonight. On GB200 with Ollama, I saw basically the same behavior. Turns out 'just one more test' was a lie.
that fixed it for me too.