Repository navigation
Conversation
tokinasin
requested review from
a team,
ggerganov,
marty1885 and
wine99
as code owners
October 9, 2026 06:22
Member
|
Generally seems ok, @ggerganov would have to weight in on the implementation. I assume there will be follow ups for at least one backend with test and conversion/loading? |
Contributor
Author
|
Added CUDA backend support and tests. |
This was referenced Oct 10, 2026
ggerganov
reviewed
Oct 15, 2026
ggerganov
reviewed
Oct 17, 2026
tokinasin
force-pushed
the
fix/cpu-yarn-no-truncate-pr1
branch
from
October 18, 2026 06:08
b2460bb to
82d7f48
Compare
Contributor
Author
|
Rebased since the Metal |
CISC
approved these changes
Oct 18, 2026
Contributor
Author
|
Thanks for the reviews so far! Since I'm limited to having two PRs open at a time, I'd appreciate it if you could take another look at this PR when you have a chance. Please let me know if there's anything else I need to address. |
tokinasin
force-pushed
the
fix/cpu-yarn-no-truncate-pr1
branch
from
October 23, 2026 01:36
82d7f48 to
c79bb16
Compare
Member
|
|
YaRN calculates correction intervals to switch frequency interpolation methods, but the setting to not round the boundaries of these intervals to integers (`truncate=false`) was not supported. Models that use `truncate=false` include gpt-oss and some PLaMo-3 models; to support them correctly, the GGML operations and CPU backend are modified to handle calculations without rounding. The default behavior is `truncate=true`, and existing calls not explicitly configured will maintain their previous behavior.
tokinasin
force-pushed
the
fix/cpu-yarn-no-truncate-pr1
branch
from
October 23, 2026 07:09
c79bb16 to
79ece22
Compare
This branch has not been deployed
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
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.
Overview
Only CPU and CUDA are currently supported, changes to other backends are to mark as unsupported.
YaRN calculates correction intervals to switch frequency interpolation methods, but the setting to not round the boundaries of these intervals to integers (
truncate=false) was not supported.Models that use
truncate=falseinclude gpt-oss and some PLaMo-3 models; to support those models correctly, the GGML operations and CPU/CUDA backends are modified to handle calculations without rounding. The default behavior istruncate=true, and existing calls not explicitly configured will maintain their previous behavior.Additional information
truncate=falseRequirements