Replies: 3 comments
|
Recently disabled with #15416, use |
0 replies
|
--context-shift doesn't seem to work with Qwen 3 VL... Inference hits a hard stop ("request (x tokens) exceeds the available context size (y tokens), try increasing it") [where x > y] |
0 replies
|
Same here: |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
It is my understanding that context shift is enabled by default... I've noticed that some models don't appear to support context shift and come to a dead stop (no more response generation) when the context length is reached while others will entertain longer contexts happily.
Is there some parameter I could be missing or is this a know limitation of some models?
All reactions