model: add llama 4 scaling for mistral-large (deepseek arch) #17744
+22
−0
Conversation
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
CISC
approved these changes
Dec 3, 2025
Contributor
|
I cherry-picked this commit onto the current latest master 08f9d3c and loaded a 4.94bpw quant of Mistral Large 3 675B Instruct with 32k sequence length, and it does produce coherent text both on a short prompt of 1.5k tokens and a longer prompt of around 19k tokens. |
Collaborator
Author
|
@DocShotgun thanks for testing, I guess it's good to merge then |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
Cont #17730
This should allow Mistral Large to go past 16K context length (hopefully, someone with enough VRAM can verify if this works or not)