Skip to content

Conversation

@ngxson
Copy link
Collaborator

@ngxson ngxson commented Nov 20, 2025

Ref: #17381 (comment)

  • Use uint64_t to align with the rest of the code base
  • Add reference to the original PR, so the comments have some context

@ngxson ngxson requested a review from ggerganov as a code owner November 20, 2025 16:33
@ngxson ngxson requested review from pwilkin and removed request for ggerganov November 20, 2025 16:33
Copy link
Collaborator

@pwilkin pwilkin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, my bad, should've used a system-independent data type to begin with (but see comment on condition).

throw std::runtime_error(std::string("expecting ',' at ") + pos);
}
if (min_times > MAX_REPETITION_THRESHOLD || (max_times != UINT64_MAX && max_times > MAX_REPETITION_THRESHOLD)) {
if (min_times > MAX_REPETITION_THRESHOLD || max_times > MAX_REPETITION_THRESHOLD) {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is going to be wrong. The condition was "if min_times exceeds threshold or (max_times is defined and exceeds threshold)". Now, this is going to trigger if max_times is not defined (so with X{n,} patterns)

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If we're not going to use std::optional like I wanted in the first approach, then I think this is the only way to do it. This is bascially equivalent to checking for == -1 or, as the original test had it, < 0.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hmm ok I thought one of the condition was overlapping the other.

using uint_max as a special value is fine, the main advantage of std::optional is its readability which is easy to replicate: c0b9903

@pwilkin
Copy link
Collaborator

pwilkin commented Nov 20, 2025

LGTM now.

@pwilkin
Copy link
Collaborator

pwilkin commented Nov 20, 2025

(I can't merge BTW so you'll have to get someone with write access to approve a review)

@ngxson
Copy link
Collaborator Author

ngxson commented Nov 20, 2025

For extra safe, I'll merge when the windows CI on my fork passes (skipping long waiting line on the main repo)

@ngxson ngxson requested a review from ggerganov November 20, 2025 17:17
@ngxson ngxson requested a review from danbev November 20, 2025 17:18
@ngxson ngxson merged commit 054a45c into master Nov 20, 2025
59 of 65 checks passed
SamuelOliveirads pushed a commit to SamuelOliveirads/llama.cpp that referenced this pull request Dec 29, 2025
* grammar : fix JSON Schema for string regex with top-level alt. (ggml-org#9903)

Prior to this commit, using a JSON Schema containing a string
with `pattern` regular expression that uses top-level alternation
(e.g. `"pattern": "^A|B|C|D$"`) would result in invalid JSON
output from the constrained sampling grammar, because it
ended up creating a grammar rule like this for the string:

```
thing ::= "\"" "A" | "B" | "C" | "D" "\"" space
```

Note that this rule will only match a starting quote for the "A" case,
and will only match an ending quote for the "D" case,
so this rule will always produce invalid JSON when used for sampling
(that is, the JSON will always be lacking the starting quote,
the ending quote, or both).

This was fixed in a simple way by adding parentheses to the
generated rule (for all string pattern rules, to keep it simple),
such that the new generated rule looks like this (correct):

```
thing ::= "\"" ("A" | "B" | "C" | "D") "\"" space
```

* grammars : add English-only grammar (ggml-org#10612)

* grammar : handle maxItems == 0 in JSON schema (ggml-org#13117)

Co-authored-by: Richard Lyons <frob@cloudstaff.com>

* grammar-parser : fix possible null-deref (ggml-org#9004)

Fixes: https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=70680

Signed-off-by: David Korczynski <david@adalogics.com>

* llama : fix typo in llama-grammar.h [no ci] (ggml-org#11816)

* * server: fix "--grammar-file" parameter (ggml-org#12285)

* common : use std::string_view now that we target c++17 (ggml-org#14319)

* json : support `enum` values within `allOf` (ggml-org#15830)

* grammar : use int64_t to avoid int overflows in int schema to grammar conversion logic (ggml-org#16626)

* grammar : support array references in json schema (ggml-org#16792)

* grammar : support array references in json schema

* Update json-schema-to-grammar.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* grammar : improve regex when naming ref derived rules

* grammar : replace non-conformant definitions array with anyOf test case

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
# Conflicts:
#	tests/test-json-schema-to-grammar.cpp

* merge fix

* llama : minor grammar refactor (ggml-org#10897)

* llama: fix error on bad grammar (ggml-org#12628)

* grammar : fix integer overflow (ggml-org#17381)

* Fix DoS / integer overflow

* Remove optional, use INT64_MAX instead as placeholder value (it's technically -1, so it fits :)

* White space

* Actually, since it's unsigned, use UINT64_MAX
# Conflicts:
#	src/llama-grammar.cpp

* grammar: fix regression caused by ggml-org#17381 (ggml-org#17412)

* grammar: fix regression caused by ggml-org#17381

* more readable
# Conflicts:
#	src/llama-grammar.cpp

* Merge Fix

* Fix warnings

---------

Signed-off-by: David Korczynski <david@adalogics.com>
Co-authored-by: Joe Eli McIlvain <joe.eli.mac@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: frob <rick+github@frob.com.au>
Co-authored-by: Richard Lyons <frob@cloudstaff.com>
Co-authored-by: DavidKorczynski <david@adalogics.com>
Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Aldehir Rojas <hello@alde.dev>
Co-authored-by: Olivier Chafik <olivier.chafik@gmail.com>
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Anico2 added a commit to Anico2/llama.cpp that referenced this pull request Jan 15, 2026
* grammar: fix regression caused by ggml-org#17381

* more readable
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants