llama : infill sampling handle very long tokens #9924
Merged
Conversation
This file contains 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
drollings
pushed a commit
to drollings/llama.cpp
that referenced
this pull request
Oct 18, 2024
* llama : infill sampling handle very long tokens ggml-ci * cont : better indices ggml-ci
dsx1986
pushed a commit
to dsx1986/llama.cpp
that referenced
this pull request
Oct 29, 2024
* llama : infill sampling handle very long tokens ggml-ci * cont : better indices ggml-ci
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
* llama : infill sampling handle very long tokens ggml-ci * cont : better indices ggml-ci
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
* llama : infill sampling handle very long tokens ggml-ci * cont : better indices ggml-ci
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Outdated suggestions cannot be applied.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.
cont #9896
The infill sampler now handles correctly tokens with very long texts (e.g. line indentations). The token-merging logic should be more clear as well.
API changes
llama_token_is_prefix. It was technically incorrect for very long tokens and I don't want to make it allocate too much stack memory as we have no upper bound for the token string length.