+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: vLLM / SGLang (https://www.datasculpting.ai/inference/forumdisplay.php?fid=36)
+--- Thread: prefill/decode separation in practice (/showthread.php?tid=138)
Pages:
1
2
Re: prefill/decode separation in practice - mangofield33 - 09-08-2026
Quote:Appreciate the detail. That matches what I saw on M3 Max. I got better results once I stopped chasing one metric and just looked at whether the workfl
I'd start with the simpler stack.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: prefill/decode separation in practice - cudapoint - 09-09-2026
My first guess would be this: On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: prefill/decode separation in practice - oxidemixer - 09-12-2026
Quote:My first guess would be this: On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glam
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: prefill/decode separation in practice - audioforge - 09-12-2026
I'd start with the simpler stack.
Re: prefill/decode separation in practice - cacheline - 09-12-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.