common: ensure token addition to batch does not exceed llama_batch size #9668
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
ggerganov
reviewed
Sep 28, 2024
There was a problem hiding this comment.
A more elegant solution is to use the fact that llama_batch.seq_id is null-terminated:
Line 20778 in 877a04c
We can add an assert directly in llama_batch_add:
GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded");
|
That's great @ggerganov. I'm uploading the new patch soon. |
github-actions
bot
added
build
A crash was observed when the number of tokens added to a batch exceeds llama_batch size. An assertion in llama_batch_add was added to protect against llama_batch size overflow.
matiaslin
force-pushed
the
protect_parallel
branch
from
d063cf1 to
c197f0f
Compare
|
Done. Now the issued mentioned in #9667 displays the following message if we attempt to add more tokens than batch size: |
matiaslin
changed the title
ggerganov
approved these changes
Sep 29, 2024
ggerganov
added
the
merge ready
|
Tks @matiaslin and @ggerganov |
dsx1986
pushed a commit
to dsx1986/llama.cpp
that referenced
this pull request
Oct 29, 2024
…9668) A crash was observed when the number of tokens added to a batch exceeds llama_batch size. An assertion in llama_batch_add was added to protect against llama_batch size overflow.
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 15, 2024
…9668) A crash was observed when the number of tokens added to a batch exceeds llama_batch size. An assertion in llama_batch_add was added to protect against llama_batch size overflow.
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Nov 18, 2024
…9668) A crash was observed when the number of tokens added to a batch exceeds llama_batch size. An assertion in llama_batch_add was added to protect against llama_batch size overflow.
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.
fix #9667
A crash was observed when the number of tokens added to a batch exceeds the context size. Assertions have been added to ensure the number of tokens added to batch is within bounds of context size.