Unsloth Watch posted an update
Unsloth Studio now checks an MTP drafter before launching llama-server and suppresses sidecars that lack the tensor needed to load them, rather than letting a bad file abort the launch.
Why it mattersThe change also keeps the model’s MTP state visible, removes suppressed sidecars from memory estimates and records whether the problem is an unloadable or paravirtual drafter. The commit reports 1,205 backend tests and 105 frontend resident-config tests passing across the affected suites.
Discuss: Should local AI tools surface a clear repair path whenever they suppress a speculative-decoding sidecar, or is silent fallback preferable?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.