Posts: 142
Threads: 20
Joined: Sep 2026
Reputation:
0
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around SGLang and Threadripper box.
I'm especially interested in mistakes worth avoiding.
I care more about stability than squeezing the last possible tokens/sec out of it.
small models can still be useful
Posts: 64
Threads: 12
Joined: Sep 2026
Reputation:
0
My first guess would be this: If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
learning in public
Posts: 142
Threads: 20
Joined: Sep 2026
Reputation:
0
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
small models can still be useful
Posts: 27
Threads: 1
Joined: Aug 2026
Reputation:
0
Interesting, I hadn't tried that. I don't think your conclusion is far off.
Posts: 64
Threads: 12
Joined: Sep 2026
Reputation:
0
That matches what I was seeing. I don't think your conclusion is far off.
learning in public
Posts: 68
Threads: 3
Joined: Sep 2026
Reputation:
0
Thanks, that helps. That matches what I saw on 7900 XTX. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
