09-28-2026, 03:38 PM
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.
learning in public
|
Embeddings discussion
|
|
09-28-2026, 03:38 PM
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal.
learning in public
09-29-2026, 03:56 PM
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal.
10-01-2026, 04:40 AM
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
measure twice, benchmark three times
|
|
« Next Oldest | Next Newest »
|