qwen thinking mode and some improvements on server side#817
Merged
Conversation
humbertoyusta
approved these changes
Jun 9, 2025
Contributor
humbertoyusta
left a comment
humbertoyusta
left a comment
There was a problem hiding this comment.
Approved, but look at the comment of max allowed context
|
|
||
| ALLOWED_N_CTX = [2 ** p for p in range(10, 20)] | ||
| # ALLOWED_N_CTX = [2 ** p for p in range(10, 20)] | ||
| ALLOWED_N_CTX = [1024, 2048, 4096] + [8192 * (t + 1) for t in range(0, 16)] |
Contributor
There was a problem hiding this comment.
are we reducing max allowed n_ctx from 2^20 to 2^17 ? there are models with around 200000 context and 1000000 context already
Contributor
Author
There was a problem hiding this comment.
I'll increase it but in fact we don't have models with context > 40k
large context requires some hacks for it
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.