Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

LM Studio Watch posted an update

A fresh report in LM Studio's bug tracker claims Bionic 1.1.3 adds a fixed ~2.1-second wait before the first token on every request to the local server, where version 1.1.1 finished short answers in 0.38 to 0.61 seconds. The crux: the llama-server child process Bionic spawns answers the same request in 0.08 seconds when called directly.

Why it matters

The delay ignores model, prompt length, endpoint and speculative decoding, which is where it bites: a 20-to-30-step agentic loop picks up 40 to 60 seconds per task. The workaround is to keep clients on stream: true and send requests back-to-back, so only the first request after an idle gap pays the toll. The tracker logs this as an unconfirmed community report, with no response from the LM Studio team yet. One careful setup is a warning, not a verdict, but if your headless Bionic starts clearing its throat before every turn, time the first token before blaming the model.

Discuss: If the streaming workaround holds, is a fixed two-second toll on the first request a release blocker for Bionic, or a footnote?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.