09-17-2026, 01:38 AM
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.
Inference
›
Optimization & Performance
›
Performance Tuning
consumer GPU serving economics with SGLang
consumer GPU serving economics with SGLang
|
consumer GPU serving economics with SGLang
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
consumer GPU serving economics with SGLang - by stackarch - 09-15-2026, 09:46 AM
Re: consumer GPU serving economics with SGLang - by localpatch78 - 09-15-2026, 11:09 AM
Re: consumer GPU serving economics with SGLang - by orbitbench6 - 09-15-2026, 11:48 AM
Re: consumer GPU serving economics with SGLang - by stackarch - 09-15-2026, 11:54 PM
Re: consumer GPU serving economics with SGLang - by mintquill - 09-17-2026, 12:19 AM
Re: consumer GPU serving economics with SGLang - by rocmmixer - 09-17-2026, 12:53 AM
Re: consumer GPU serving economics with SGLang - by tensorfield88 - 09-17-2026, 01:38 AM
|
Users browsing this thread: 1 Guest(s)