Fix memory bug in grammar parser #7194
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
jart
added a commit
to Mozilla-Ocho/llamafile
that referenced
this pull request
May 10, 2024
This important change was accidentally removed in 94d0940. Credit for discovering (and most importantly, reporting) this issue goes to Eclypsium Security Researcher Richard Johnson. Bug fix sent upstream in ggerganov/llama.cpp#7194
mofosyne
added
bugfix
mofosyne
approved these changes
May 10, 2024
There was a problem hiding this comment.
Observations:
-
common/common.cpp : gpt_params_parse_ex() now throws an invalid parameter right at the point of of argument
-
common/grammar-parser.cpp : grammar_parser() now throws for when string unexpectedly end while searching for closing characters
"or](as well as after-within square brackets) -
examples/llava/llava-cli.cpp : process_prompt() will now exit(1) when llama_sampling_init() fails to initialize
-
examples/main/main.cpp : main() will now exit(1) when llama_sampling_init() fails to initialize
CI test failed, but unsure on cause of error. Subprocess aborted? Might be a CI fluke?
18 - test-grammar-integration (Subprocess aborted)
24 - test-json-schema-to-grammar (Subprocess aborted)
The llama.cpp grammar parser had a bug where forgetting to add a closing
quotation mark to strings would cause parsing to crash. Anyone running a
server on a public endpoint is advised to upgrade. To reproduce this bug
./llamafile -m foo.gguf -p bar --grammar 'root::="'
Credit for discovering and reporting this issue goes to Eclypsium
Security Researcher Richard Johnson <Richard.johnson@eclypsium.com>.
mofosyne
reviewed
May 10, 2024
ExtReMLapin
added a commit
to ExtReMLapin/llama-cpp-python
that referenced
this pull request
Jul 29, 2024
abetlen
added a commit
to abetlen/llama-cpp-python
that referenced
this pull request
Aug 7, 2024
…on (#1637) * Backported . (any chat) from llama.cpp * unfinished {count,optionalmax) * implemented slice function in std:vector * fixed mistake done while reading * ported ggerganov/llama.cpp#7194 * multiple fixes, var copy * Rewrite LlamaGrammar internals in python style * bugfix --------- Co-authored-by: Andrei <abetlen@gmail.com>
francomattar
added a commit
to francomattar/Python-llama-cpp
that referenced
this pull request
Dec 13, 2024
…on (#1637)
* Backported . (any chat) from llama.cpp
* unfinished {count,optionalmax)
* implemented slice function in std:vector
* fixed mistake done while reading
* ported ggerganov/llama.cpp#7194
* multiple fixes, var copy
* Rewrite LlamaGrammar internals in python style
* bugfix
---------
Co-authored-by: Andrei <abetlen@gmail.com>
nayanzin33sergey
added a commit
to nayanzin33sergey/Python-llama-cpp
that referenced
this pull request
Dec 18, 2024
…on (#1637)
* Backported . (any chat) from llama.cpp
* unfinished {count,optionalmax)
* implemented slice function in std:vector
* fixed mistake done while reading
* ported ggerganov/llama.cpp#7194
* multiple fixes, var copy
* Rewrite LlamaGrammar internals in python style
* bugfix
---------
Co-authored-by: Andrei <abetlen@gmail.com>
jamesdev9
pushed a commit
to jamesdev9/python-llama-cpp
that referenced
this pull request
Dec 22, 2024
…on (#1637)
* Backported . (any chat) from llama.cpp
* unfinished {count,optionalmax)
* implemented slice function in std:vector
* fixed mistake done while reading
* ported ggerganov/llama.cpp#7194
* multiple fixes, var copy
* Rewrite LlamaGrammar internals in python style
* bugfix
---------
Co-authored-by: Andrei <abetlen@gmail.com>
NoBrainer242
pushed a commit
to NoBrainer242/Python-App-llama
that referenced
this pull request
Dec 27, 2024
…on (#1637)
* Backported . (any chat) from llama.cpp
* unfinished {count,optionalmax)
* implemented slice function in std:vector
* fixed mistake done while reading
* ported ggerganov/llama.cpp#7194
* multiple fixes, var copy
* Rewrite LlamaGrammar internals in python style
* bugfix
---------
Co-authored-by: Andrei <abetlen@gmail.com>
NoBrainer24
added a commit
to NoBrainer24/Python-App-llama-
that referenced
this pull request
Dec 28, 2024
…on (#1637)
* Backported . (any chat) from llama.cpp
* unfinished {count,optionalmax)
* implemented slice function in std:vector
* fixed mistake done while reading
* ported ggerganov/llama.cpp#7194
* multiple fixes, var copy
* Rewrite LlamaGrammar internals in python style
* bugfix
---------
Co-authored-by: Andrei <abetlen@gmail.com>
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.
The llama.cpp grammar parser had a bug where forgetting to add a closing quotation mark to strings would cause parsing to crash. Anyone running a server on a public endpoint is advised to upgrade. To reproduce this bug
Credit for discovering and reporting this issue goes to Eclypsium Security Researcher Richard Johnson Richard.johnson@eclypsium.com.