llama : refactor sampling_info to use buffer_view template#19368
Merged
danbev merged 4 commits intoFeb 11, 2026
Conversation
This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
ggerganov
reviewed
Feb 5, 2026
ggerganov
reviewed
Feb 10, 2026
ggerganov
left a comment
ggerganov
left a comment
Member
There was a problem hiding this comment.
For consistency, the non-sampling logits and embeddings could be wrapped in buffer view as well
This commit applies the same changes as was done previously for the sampling_info struct where some of the members were updated to use buffer_view. In this commit, the logits and embd members of llama_context are updated to use buffer_view instead of raw pointers and separate size for consistency.
ggerganov
approved these changes
Feb 10, 2026
ggerganov
left a comment
ggerganov
left a comment
Member
There was a problem hiding this comment.
Can merge if the CI is green
The previous commit updated the resetting of the logits and embd pointer by resetting the entire buffer_view. But original version only reset the data pointers and not the size. This commit updates the resetting to only reset the data pointers and not the size to match the original functionality. In this way the size is preserved and not reset to 0.
liparetejas
pushed a commit
to liparetejas/llama.cpp
that referenced
this pull request
Feb 23, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 2, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
ljubomirj
pushed a commit
to ljubomirj/llama.cpp
that referenced
this pull request
May 6, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
my-other-github-account
pushed a commit
to my-other-github-account/llama.cpp
that referenced
this pull request
May 15, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
my-other-github-account
pushed a commit
to my-other-github-account/llama.cpp
that referenced
this pull request
May 15, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
fewtarius
pushed a commit
to fewtarius/llama.cpp
that referenced
this pull request
May 30, 2026
…19368) * llama : refactor sampling_info to use buffer_view template This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers. The motivation for this is to simplify the code, improve type safety and readability.
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.
This commit updates the sampling_info struct in llama-context to use a buffer_view template for the logits, probs, sampled tokens, and candidates buffers.
The motivation for this is to simplify the code, improve type safety and readability.