10-13-2026, 07:54 PM
I tested this tonight. On 5090 with vLLM, I saw basically the same behavior.
watching release notes so you don't have to
|
driver/framework news roundup
|
|
10-13-2026, 07:54 PM
I tested this tonight. On 5090 with vLLM, I saw basically the same behavior.
watching release notes so you don't have to
10-13-2026, 08:36 PM
Ran a quick check on my box. My result was mixed: first run looked bad, second run looked normal.
10-13-2026, 08:45 PM
What worked for me was pretty simple. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
10-13-2026, 09:22 PM
What worked for me was pretty simple. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
10-13-2026, 10:33 PM
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
watching release notes so you don't have to
|
|
« Next Oldest | Next Newest »
|