Posts: 121
Threads: 15
Joined: Sep 2026
Reputation:
0
Wanted to compare notes with people doing similar things.
I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling embeddings.
Not looking for the perfect answer, mostly what worked in real use.
image models by night, local pipelines by day
Posts: 40
Threads: 2
Joined: Sep 2026
Reputation:
0
That matches what I was seeing. I ended up in about the same place using vLLM. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Posts: 37
Threads: 4
Joined: Aug 2026
Reputation:
0
Good point. The pattern around router policy has been pretty similar for me.
Posts: 48
Threads: 8
Joined: Oct 2026
Reputation:
0
that fixed it for me too.
Posts: 51
Threads: 6
Joined: Aug 2026
Reputation:
0
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
serving stack tinkerer
Posts: 27
Threads: 1
Joined: Sep 2026
Reputation:
0
Interesting, I hadn't tried that. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
learning in public
Posts: 42
Threads: 10
Joined: Aug 2026
Reputation:
0
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.
Posts: 121
Threads: 15
Joined: Sep 2026
Reputation:
0
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at speculative decoding. Once you know the plain path works, then add the faster path back in piece by piece.
image models by night, local pipelines by day
