good hosted AI app that still respects privacy with SGLang

[torchsmith25]

This keeps coming up in conversation so I figured I'd start a thread.

One thing I keep noticing is that people underestimate prefill/decode split until they actually try to run this stuff for more than one afternoon.

Wondering if this is just where the whole space is heading now.

[vramarch]

This keeps coming up in conversation so I figured I'd start a thread.

same here on my side.

[llm_wren]

I think the bottleneck is somewhere else. I've seen people blame consumer GPUs when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[emberquill]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[sparrowshed]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal.

[rocmpath]

I'd start with the simpler stack.

[amberplane]

Not sure I agree there. I've seen people blame batch size when the real issue was much more mundane.

[emberrunner]

subscribed, curious where this lands.

[modbench]

A couple things I'd check first. On Threadripper box, 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.

[embershed99]

Good point. The pattern around token cost has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.