sampling : remove sampling branching in output_reserve#18811
Merged
Conversation
danbev
force-pushed
the
sampling-output-reserve
branch
from
58b5299 to
9d9be8b
Compare
This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
danbev
force-pushed
the
sampling-output-reserve
branch
from
9d9be8b to
4c6dcc4
Compare
Member
Author
|
@ggerganov When you get a chance could you take a look at this and see if this is what you had in mind? |
ggerganov
reviewed
Jan 26, 2026
This reverts commit 4c6dcc4.
This commit always allocates backend buffers for all sequences if backend samplers have been configured in the context regardless if the current batch has any sequences that require backend sampling or not.
This commit adds a new function `needs_cpu_logits` to determine whether CPU logits are needed for sampling. This avoids unnecessary copying of logits when all sequences use backend sampling.
ggerganov
reviewed
Jan 27, 2026
ggerganov
reviewed
Jan 27, 2026
ggerganov
approved these changes
Jan 27, 2026
Member
ggerganov
left a comment
ggerganov
left a comment
There was a problem hiding this comment.
Should be OK to merge after the CI pass
shaofeiqi
pushed a commit
to qualcomm/llama.cpp
that referenced
this pull request
Feb 6, 2026
* sampling : remove sampling branching in output_reserve This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
* sampling : remove sampling branching in output_reserve This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
ljubomirj
pushed a commit
to ljubomirj/llama.cpp
that referenced
this pull request
May 6, 2026
* sampling : remove sampling branching in output_reserve This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
my-other-github-account
pushed a commit
to my-other-github-account/llama.cpp
that referenced
this pull request
May 15, 2026
* sampling : remove sampling branching in output_reserve This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
my-other-github-account
pushed a commit
to my-other-github-account/llama.cpp
that referenced
this pull request
May 15, 2026
* sampling : remove sampling branching in output_reserve This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
fewtarius
pushed a commit
to fewtarius/llama.cpp
that referenced
this pull request
May 30, 2026
* sampling : remove sampling branching in output_reserve This commit updates output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch. The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.
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 output_reserve in llama-context.cpp to always allocate sampling buffers regardless of whether sampling is needed for the current batch.
The motivation for this is to avoid reallocations and branching based on the sampling requirements of the batch.