tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

sampling : support for llguidance grammars (#10224)

Browse Source 
* initial porting of previous LLG patch

* update for new APIs

* build: integrate llguidance as an external project

* use '%llguidance' as marker to enable llg lark syntax

* add some docs

* clarify docs

* code style fixes

* remove llguidance.h from .gitignore

* fix tests when llg is enabled

* pass vocab not model to llama_sampler_init_llg()

* copy test-grammar-integration.cpp to test-llguidance.cpp

* clang fmt

* fix ref-count bug

* build and run test

* gbnf -> lark syntax

* conditionally include llguidance test based on LLAMA_LLGUIDANCE flag

* rename llguidance test file to test-grammar-llguidance.cpp

* add gh action for llg test

* align tests with LLG grammar syntax and JSON Schema spec

* llama_tokenizer() in fact requires valid utf8

* update llg

* format file

* add $LLGUIDANCE_LOG_LEVEL support

* fix whitespace

* fix warning

* include <cmath> for INFINITY

* add final newline

* fail llama_sampler_init_llg() at runtime

* Link gbnf_to_lark.py script; fix links; refer to llg docs for lexemes

* simplify #includes

* improve doc string for LLAMA_LLGUIDANCE

* typo in merge

* bump llguidance to 0.6.12
This commit is contained in:
Michał Moskal
2025-02-01 23:55:32 -08:00
committed by GitHub
parent 0cec062a63
commit ff227703d6
13 changed files with 1555 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/CMakeLists.txt
View File

@ -86,6 +86,9 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
if (LLAMA_LLGUIDANCE)
llama_target_and_test(test-grammar-llguidance.cpp ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
endif ()
if (NOT WIN32)
# these tests are disabled on Windows because they use internal functions not exported with LLAMA_API

2
tests/test-grammar-integration.cpp
View File

@ -129,7 +129,7 @@ static void test_grammar(const std::string & test_desc, const std::string & gram
test(test_desc + ". Grammar: " + grammar_str, grammar_str, passing_strings, failing_strings);
}
static void test_schema(const std::string & test_desc, const std::string & schema_str, const std::vector<std::string> & passing_strings, const std::vector<std::string> & failing_strings) {
test(test_desc + ". Schema: " + schema_str, json_schema_to_grammar(json::parse(schema_str)), passing_strings, failing_strings);
test(test_desc + ". Schema: " + schema_str, json_schema_to_grammar(json::parse(schema_str), true), passing_strings, failing_strings);
}
static void test_simple_grammar() {

1140
tests/test-grammar-llguidance.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

2
tests/test-json-schema-to-grammar.cpp
View File

@ -1246,7 +1246,7 @@ int main() {
test_all("C++", [](const TestCase & tc) {
try {
tc.verify(json_schema_to_grammar(nlohmann::ordered_json::parse(tc.schema)));
tc.verify(json_schema_to_grammar(nlohmann::ordered_json::parse(tc.schema), true));
tc.verify_status(SUCCESS);
} catch (const std::runtime_error & ex) {
fprintf(stderr, "Error: %s\n", ex.what());