fix(rpc): prevent division by zero in deserialize_tensor#20712
Merged
rgerganov merged 2 commits intoggml-org:masterfrom Mar 21, 2026
Merged
fix(rpc): prevent division by zero in deserialize_tensor#20712rgerganov merged 2 commits intoggml-org:masterfrom
rgerganov merged 2 commits intoggml-org:masterfrom
Conversation
When receiving an RPC message with a deprecated tensor type (e.g., type 4 or 5 where `blck_size == 0`), `ggml_row_size()` will trigger a division by zero (SIGFPE) and crash the rpc-server. This patch adds a simple validation check in `deserialize_tensor` to return `nullptr` if the requested tensor type has a block size of 0. (Note: This was originally reported via Security Advisory and maintainer suggested dropping a patch here).
github-actions
Bot
added
the
ggml
rgerganov
approved these changes
Mar 18, 2026
Member
rgerganov
left a comment
rgerganov
left a comment
There was a problem hiding this comment.
ggml_blck_size performs a simple array lookup, so this shouldn't have performance impact. looks good to me.
rgerganov
approved these changes
Mar 21, 2026
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
) rpc : prevent division by zero in deserialize_tensor When receiving an RPC message with a deprecated tensor type (e.g., type 4 or 5 where `blck_size == 0`), `ggml_row_size()` will trigger a division by zero (SIGFPE) and crash the rpc-server. This patch adds a simple validation check in `deserialize_tensor` to return `nullptr` if the requested tensor type has a block size of 0. (Note: This was originally reported via Security Advisory and maintainer suggested dropping a patch here). * style: remove trailing whitespace
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
) rpc : prevent division by zero in deserialize_tensor When receiving an RPC message with a deprecated tensor type (e.g., type 4 or 5 where `blck_size == 0`), `ggml_row_size()` will trigger a division by zero (SIGFPE) and crash the rpc-server. This patch adds a simple validation check in `deserialize_tensor` to return `nullptr` if the requested tensor type has a block size of 0. (Note: This was originally reported via Security Advisory and maintainer suggested dropping a patch here). * style: remove trailing whitespace
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.
When receiving an RPC message with a deprecated tensor type (e.g., type 4 or 5 where
blck_size == 0),ggml_row_size()will trigger a division by zero (SIGFPE) and crash the rpc-server.This patch adds a simple validation check in
deserialize_tensorto returnnullptrif the requested tensor type has a block size of 0.(Note: This was originally reported via Security Advisory and maintainer suggested dropping a patch here).
Make sure to read the contributing guidelines before submitting a PR