High level conclusions

Fuzzer fuzz_inference is blocked:

The runtime code coverage of fuzz_inference covers 22.74% of its statically reachable code. This means there is some place that blocks the fuzzer to continue exploring more code at run time.

Fuzzer fuzz_structured is blocked:

The runtime code coverage of fuzz_structured covers 5.530% of its statically reachable code. This means there is some place that blocks the fuzzer to continue exploring more code at run time.

Fuzzer fuzz_load_model is blocked:

The runtime code coverage of fuzz_load_model covers 5.530% of its statically reachable code. This means there is some place that blocks the fuzzer to continue exploring more code at run time.

Fuzzer fuzz_grammar is blocked:

The runtime code coverage of fuzz_grammar covers 14.38% of its statically reachable code. This means there is some place that blocks the fuzzer to continue exploring more code at run time.

Fuzzers reach 44.34% of cyclomatic complexity.

Fuzzers reach 25.06% of all functions.

Reachability and coverage overview

Functions statically reachable by fuzzers

1333 / 5319

Cyclomatic complexity statically reachable by fuzzers

26229 / 59143

Runtime code coverage of functions

961 / 5319

The following table shows data about each function in the project. The functions included in this table correspond to all functions that exist in the executables of the fuzzers. As such, there may be functions that are from third-party libraries.

For further technical details on the meaning of columns in the below table, please see the Glossary .

Func name	Functions filename	Args	Function call depth	Reached by Fuzzers	Runtime reached by Fuzzers	Combined reached by Fuzzers	Fuzzers runtime hit	Func lines hit %	I Count	BB Count	Cyclomatic complexity	Functions reached	Reached by functions	Accumulated cyclomatic complexity	Undiscovered complexity

Fuzzer: fuzz_grammar

Call tree

The calltree shows the control flow of the fuzzer. This is overlaid with coverage information to display how much of the potential code a fuzzer can reach is in fact covered at runtime. In the following there is a link to a detailed calltree visualisation as well as a bitmap showing a high-level view of the calltree. For further information about these topics please see the glossary for full calltree and calltree overview

Call tree overview bitmap:

The distribution of callsites in terms of coloring is

Color	Runtime hitcount	Callsite count	Percentage
red	0	465	82.7%
gold	[1:9]	32	5.69%
yellow	[10:29]	17	3.02%
greenyellow	[30:49]	0	0.0%
lawngreen	50+	48	8.54%
All colors	562	100

Fuzz blockers

The following nodes represent call sites where fuzz blockers occur.

Amount of callsites blocked	Calltree index	Parent function	Callsite	Largest blocked function
420	64	parse_int(char const*)	call site: 00064	ggml_abort
5	26	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00026	__cxa_allocate_exception
5	38	parse_char(char const*)	call site: 00038	__cxa_allocate_exception
5	50	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00050	__cxa_allocate_exception
4	7	is_word_char(char)	call site: 00007	__cxa_allocate_exception
4	58	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00058	__cxa_allocate_exception
4	506	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)::$_0::operator()(unsigned long, unsigned long) const	call site: 00506	__cxa_allocate_exception
4	519	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00519	__cxa_allocate_exception
4	529	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00529	__cxa_allocate_exception
4	539	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00539	__cxa_allocate_exception
4	549	llama_grammar_parser::parse_rule(char const*)	call site: 00549	__cxa_allocate_exception
1	32	parse_char(char const*)	call site: 00032

Runtime coverage analysis

Covered functions

19

Functions that are reachable but not covered

244

Reachable functions

285

Percentage of reachable functions covered

14.39%

NB: The sum of covered functions and functions that are reachable but not covered need not be equal to Reachable functions . This is because the reachability analysis is an approximation and thus at runtime some functions may be covered that are not included in the reachability analysis. This is a limitation of our static analysis capabilities.

Function name	source code lines	source lines hit	percentage hit

Files reached

filename	functions hit
/src/llama.cpp/fuzzers/fuzz_grammar.cpp	1
/src/llama.cpp/src/llama-grammar.h	2
/src/llama.cpp/src/llama-grammar.cpp	17
/src/llama.cpp/src/llama-vocab.cpp	66
/src/llama.cpp/ggml/src/ggml.c	1
/src/llama.cpp/src/llama-impl.cpp	3
/src/llama.cpp/src/unicode.cpp	36
/usr/local/bin/../include/c++/v1/stdexcept	1
/src/llama.cpp/src/unicode.h	3

Fuzzer: fuzz_apply_template

Call tree

The calltree shows the control flow of the fuzzer. This is overlaid with coverage information to display how much of the potential code a fuzzer can reach is in fact covered at runtime. In the following there is a link to a detailed calltree visualisation as well as a bitmap showing a high-level view of the calltree. For further information about these topics please see the glossary for full calltree and calltree overview

Call tree overview bitmap:

The distribution of callsites in terms of coloring is

Color	Runtime hitcount	Callsite count	Percentage
red	0	2	2.10%
gold	[1:9]	5	5.26%
yellow	[10:29]	15	15.7%
greenyellow	[30:49]	7	7.36%
lawngreen	50+	66	69.4%
All colors	95	100

Fuzz blockers

The following nodes represent call sites where fuzz blockers occur.

Amount of callsites blocked	Calltree index	Parent function	Callsite	Largest blocked function
1	79	llm_chat_apply_template(llm_chat_template, std::__1::vector > const&, std::__1::basic_string , std::__1::allocator >&, bool)	call site: 00079
1	83	llm_chat_apply_template(llm_chat_template, std::__1::vector > const&, std::__1::basic_string , std::__1::allocator >&, bool)	call site: 00083

Runtime coverage analysis

Covered functions

7

Functions that are reachable but not covered

5

Reachable functions

17

Percentage of reachable functions covered

70.59%

NB: The sum of covered functions and functions that are reachable but not covered need not be equal to Reachable functions . This is because the reachability analysis is an approximation and thus at runtime some functions may be covered that are not included in the reachability analysis. This is a limitation of our static analysis capabilities.

Function name	source code lines	source lines hit	percentage hit

Files reached

filename	functions hit
/src/llama.cpp/fuzzers/fuzz_apply_template.cpp	1
/src/llama.cpp/src/llama.cpp	1
/src/llama.cpp/src/llama-chat.cpp	5

Fuzzer: fuzz_load_model

Call tree

The calltree shows the control flow of the fuzzer. This is overlaid with coverage information to display how much of the potential code a fuzzer can reach is in fact covered at runtime. In the following there is a link to a detailed calltree visualisation as well as a bitmap showing a high-level view of the calltree. For further information about these topics please see the glossary for full calltree and calltree overview

Call tree overview bitmap:

The distribution of callsites in terms of coloring is

Color	Runtime hitcount	Callsite count	Percentage
red	0	7580	98.6%
gold	[1:9]	71	0.92%
yellow	[10:29]	5	0.06%
greenyellow	[30:49]	9	0.11%
lawngreen	50+	16	0.20%
All colors	7681	100

Fuzz blockers

The following nodes represent call sites where fuzz blockers occur.

Amount of callsites blocked	Calltree index	Parent function	Callsite	Largest blocked function
7449	213	llama_model::~llama_model()	call site: 00213	ggml_backend_alloc_ctx_tensors_from_buft
87	87	llama_model::llama_model(llama_model_params const&)	call site: 00087	ggml_backend_dev_count
13	180	ggml_backend_dev_get	call site: 00180	ggml_backend_dev_buffer_type
12	6	ggml_init	call site: 00006	ggml_abort
10	197	ggml_backend_dev_type	call site: 00197	ggml_backend_dev_backend_reg
2	175	ggml_backend_dev_count	call site: 00175	ggml_backend_dev_get
1	19	ggml_init	call site: 00019	ggml_log_internal
1	21	ggml_aligned_malloc	call site: 00021	ggml_log_internal
1	38	llama_model_load_from_file	call site: 00038
1	41	llama_log_internal_v(ggml_log_level, char const*, __va_list_tag*)	call site: 00041	vsnprintf
1	53	ggml_cpu_init	call site: 00053	clock_gettime
1	82	get_reg()	call site: 00082

Runtime coverage analysis

Covered functions

56

Functions that are reachable but not covered

1042

Reachable functions

1103

Percentage of reachable functions covered

5.53%

NB: The sum of covered functions and functions that are reachable but not covered need not be equal to Reachable functions . This is because the reachability analysis is an approximation and thus at runtime some functions may be covered that are not included in the reachability analysis. This is a limitation of our static analysis capabilities.

Function name	source code lines	source lines hit	percentage hit

Files reached

filename	functions hit
/src/llama.cpp/fuzzers/fuzz_load_model.cpp	2
/src/llama.cpp/src/llama.cpp	10
/src/llama.cpp/ggml/src/ggml.c	71
/src/llama.cpp/ggml/src/ggml-threading.cpp	2
/src/llama.cpp/src/llama-impl.cpp	10
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	13
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp	1
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c	1
/src/llama.cpp/ggml/src/./ggml-impl.h	5
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	2
/src/llama.cpp/ggml/src/ggml-backend.cpp	50
/src/llama.cpp/src/llama-model.cpp	33
/src/llama.cpp/src/llama-vocab.cpp	88
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	33
/src/llama.cpp/src/llama-hparams.cpp	20
/src/llama.cpp/src/llama-adapter.h	1
/src/llama.cpp/src/llama-model-loader.cpp	96
/src/llama.cpp/src/llama-arch.cpp	9
/src/llama.cpp/ggml/src/gguf.cpp	81
/src/llama.cpp/src/llama-mmap.cpp	29
/src/llama.cpp/src/llama-model-loader.h	2
/src/llama.cpp/src/unicode.cpp	38
/usr/local/bin/../include/c++/v1/stdexcept	1
/src/llama.cpp/src/unicode.h	3
/src/llama.cpp/src/llama-arch.h	3
/src/llama.cpp/ggml/src/ggml-impl.h	1
/src/llama.cpp/ggml/src/ggml-alloc.c	7
/src/llama.cpp/ggml/src/ggml-quants.c	10

Fuzzer: fuzz_structured

Call tree

The calltree shows the control flow of the fuzzer. This is overlaid with coverage information to display how much of the potential code a fuzzer can reach is in fact covered at runtime. In the following there is a link to a detailed calltree visualisation as well as a bitmap showing a high-level view of the calltree. For further information about these topics please see the glossary for full calltree and calltree overview

Call tree overview bitmap:

The distribution of callsites in terms of coloring is

Color	Runtime hitcount	Callsite count	Percentage
red	0	7580	98.6%
gold	[1:9]	76	0.98%
yellow	[10:29]	9	0.11%
greenyellow	[30:49]	2	0.02%
lawngreen	50+	19	0.24%
All colors	7686	100

Fuzz blockers

The following nodes represent call sites where fuzz blockers occur.

Amount of callsites blocked	Calltree index	Parent function	Callsite	Largest blocked function
7449	217	llama_model::~llama_model()	call site: 00217	ggml_backend_alloc_ctx_tensors_from_buft
87	91	llama_model::llama_model(llama_model_params const&)	call site: 00091	ggml_backend_dev_count
13	184	ggml_backend_dev_get	call site: 00184	ggml_backend_dev_buffer_type
12	6	ggml_init	call site: 00006	ggml_abort
10	201	ggml_backend_dev_type	call site: 00201	ggml_backend_dev_backend_reg
2	179	ggml_backend_dev_count	call site: 00179	ggml_backend_dev_get
1	19	ggml_init	call site: 00019	ggml_log_internal
1	21	ggml_aligned_malloc	call site: 00021	ggml_log_internal
1	42	llama_model_load_from_file	call site: 00042
1	45	llama_log_internal_v(ggml_log_level, char const*, __va_list_tag*)	call site: 00045	vsnprintf
1	57	ggml_cpu_init	call site: 00057	clock_gettime
1	86	get_reg()	call site: 00086

Runtime coverage analysis

Covered functions

56

Functions that are reachable but not covered

1042

Reachable functions

1103

Percentage of reachable functions covered

5.53%

NB: The sum of covered functions and functions that are reachable but not covered need not be equal to Reachable functions . This is because the reachability analysis is an approximation and thus at runtime some functions may be covered that are not included in the reachability analysis. This is a limitation of our static analysis capabilities.

Function name	source code lines	source lines hit	percentage hit

Files reached

filename	functions hit
/src/llama.cpp/fuzzers/fuzz_structured.cpp	2
/src/llama.cpp/src/llama.cpp	10
/src/llama.cpp/ggml/src/ggml.c	71
/src/llama.cpp/ggml/src/ggml-threading.cpp	2
/src/llama.cpp/src/llama-impl.cpp	10
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	13
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp	1
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c	1
/src/llama.cpp/ggml/src/./ggml-impl.h	5
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	2
/src/llama.cpp/ggml/src/ggml-backend.cpp	50
/src/llama.cpp/src/llama-model.cpp	33
/src/llama.cpp/src/llama-vocab.cpp	88
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	33
/src/llama.cpp/src/llama-hparams.cpp	20
/src/llama.cpp/src/llama-adapter.h	1
/src/llama.cpp/src/llama-model-loader.cpp	96
/src/llama.cpp/src/llama-arch.cpp	9
/src/llama.cpp/ggml/src/gguf.cpp	81
/src/llama.cpp/src/llama-mmap.cpp	29
/src/llama.cpp/src/llama-model-loader.h	2
/src/llama.cpp/src/unicode.cpp	38
/usr/local/bin/../include/c++/v1/stdexcept	1
/src/llama.cpp/src/unicode.h	3
/src/llama.cpp/src/llama-arch.h	3
/src/llama.cpp/ggml/src/ggml-impl.h	1
/src/llama.cpp/ggml/src/ggml-alloc.c	7
/src/llama.cpp/ggml/src/ggml-quants.c	10

Fuzzer: fuzz_json_to_grammar

Call tree

The calltree shows the control flow of the fuzzer. This is overlaid with coverage information to display how much of the potential code a fuzzer can reach is in fact covered at runtime. In the following there is a link to a detailed calltree visualisation as well as a bitmap showing a high-level view of the calltree. For further information about these topics please see the glossary for full calltree and calltree overview

Call tree overview bitmap:

The distribution of callsites in terms of coloring is

Color	Runtime hitcount	Callsite count	Percentage
red	0	368	43.2%
gold	[1:9]	3	0.35%
yellow	[10:29]	9	1.05%
greenyellow	[30:49]	1	0.11%
lawngreen	50+	470	55.2%
All colors	851	100

Fuzz blockers

The following nodes represent call sites where fuzz blockers occur.

Amount of callsites blocked	Calltree index	Parent function	Callsite	Largest blocked function
93	472	void nlohmann::json_abi_v3_12_0::detail::external_constructor<(nlohmann::json_abi_v3_12_0::detail::value_t)6>::construct , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> >(nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>&, nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::number_unsigned_t)	call site: 00472	_ZN8nlohmann16json_abi_v3_12_06detail11parse_error6createIDnTnNSt3__19enable_ifIXsr21is_basic_json_contextIT_EE5valueEiE4typeELi0EEES2_iRKNS1_10position_tERKNS4_12basic_stringIcNS4_11char_traitsIcEENS4_9allocatorIcEEEES6_
39	242	nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::end()	call site: 00242	_ZN8nlohmann16json_abi_v3_12_010basic_jsonINSt3__13mapENS2_6vectorENS2_12basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEblmdS8_NS0_14adl_serializerENS4_IhNS8_IhEEEEvE5eraseINS0_6detail9iter_implISE_EETnNS2_9enable_ifIXoosr3std7is_sameIT_SI_EE5valuesr3std7is_sameISK_NSH_IKSE_EEEE5valueEiE4typeELi0EEESK_SK_
21	370	_ZN8nlohmann16json_abi_v3_12_010basic_jsonINSt3__13mapENS2_6vectorENS2_12basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEblmdS8_NS0_14adl_serializerENS4_IhNS8_IhEEEEvEC2IRSA_SA_TnNS2_9enable_ifIXaantsr6detail13is_basic_jsonIT0_EE5valuesr6detail18is_compatible_typeISE_SI_EE5valueEiE4typeELi0EEEOT_	call site: 00370	_ZN8nlohmann16json_abi_v3_12_06detail11parse_error6createIDnTnNSt3__19enable_ifIXsr21is_basic_json_contextIT_EE5valueEiE4typeELi0EEES2_iRKNS1_10position_tERKNS4_12basic_stringIcNS4_11char_traitsIcEENS4_9allocatorIcEEEES6_
16	392	std::__1::basic_string , std::__1::allocator > nlohmann::json_abi_v3_12_0::detail::concat , std::__1::allocator >, char const (&) [23], std::__1::basic_string , std::__1::allocator > >(char const (&) [23], std::__1::basic_string , std::__1::allocator >&&)	call site: 00392	_ZN8nlohmann16json_abi_v3_12_06detail12out_of_range6createIPNS0_10basic_jsonINSt3__13mapENS5_6vectorENS5_12basic_stringIcNS5_11char_traitsIcEENS5_9allocatorIcEEEEblmdSB_NS0_14adl_serializerENS7_IhNSB_IhEEEEvEETnNS5_9enable_ifIXsr21is_basic_json_contextIT_EE5valueEiE4typeELi0EEES2_iRKSD_SK_
15	218	nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::json_value::json_value(std::__1::basic_string , std::__1::allocator > const&)	call site: 00218
15	345	nlohmann::json_abi_v3_12_0::detail::parse_error::parse_error(int, unsigned long, char const*)	call site: 00345	_ZN8nlohmann16json_abi_v3_12_010basic_jsonINSt3__13mapENS2_6vectorENS2_12basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEblmdS8_NS0_14adl_serializerENS4_IhNS8_IhEEEEvEC2IRSA_SA_TnNS2_9enable_ifIXaantsr6detail13is_basic_jsonIT0_EE5valuesr6detail18is_compatible_typeISE_SI_EE5valueEiE4typeELi0EEEOT_
12	801	nlohmann::json_abi_v3_12_0::byte_container_with_subtype > > const& nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::get_ref_impl > > const&, nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> const>(nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> const&)	call site: 00801	_ZN8nlohmann16json_abi_v3_12_014adl_serializerINS0_27byte_container_with_subtypeINSt3__16vectorIhNS3_9allocatorIhEEEEEEvE7to_jsonINS0_10basic_jsonINS0_11ordered_mapES4_NS3_12basic_stringIcNS3_11char_traitsIcEENS5_IcEEEEblmdS5_S1_S7_vEERKS8_EEDTcmclL_ZNS0_7to_jsonEEfp_clsr3stdE7forwardIT0_Efp0_EEcvv_EERT_OSL_
10	183	nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::operator=(nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>)	call site: 00183	__cxa_allocate_exception
10	411	_ZN8nlohmann16json_abi_v3_12_06detail12out_of_range6createIDnTnNSt3__19enable_ifIXsr21is_basic_json_contextIT_EE5valueEiE4typeELi0EEES2_iRKNS4_12basic_stringIcNS4_11char_traitsIcEENS4_9allocatorIcEEEES6_	call site: 00411	_ZN8nlohmann16json_abi_v3_12_010basic_jsonINSt3__13mapENS2_6vectorENS2_12basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEblmdS8_NS0_14adl_serializerENS4_IhNS8_IhEEEEvEC2IRddTnNS2_9enable_ifIXaantsr6detail13is_basic_jsonIT0_EE5valuesr6detail18is_compatible_typeISE_SI_EE5valueEiE4typeELi0EEEOT_
8	172	nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::data::~data()	call site: 00172
8	204	nlohmann::json_abi_v3_12_0::detail::out_of_range::out_of_range(int, char const*)	call site: 00204	__cxa_throw
8	440	void nlohmann::json_abi_v3_12_0::detail::external_constructor<(nlohmann::json_abi_v3_12_0::detail::value_t)4>::construct , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> >(nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>&, nlohmann::json_abi_v3_12_0::basic_json , std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::boolean_t)	call site: 00440	_ZN8nlohmann16json_abi_v3_12_010basic_jsonINSt3__13mapENS2_6vectorENS2_12basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEblmdS8_NS0_14adl_serializerENS4_IhNS8_IhEEEEvEC2IRllTnNS2_9enable_ifIXaantsr6detail13is_basic_jsonIT0_EE5valuesr6detail18is_compatible_typeISE_SI_EE5valueEiE4typeELi0EEEOT_

Runtime coverage analysis

Covered functions

511

Functions that are reachable but not covered

160

Reachable functions

675

Percentage of reachable functions covered

76.3%

NB: The sum of covered functions and functions that are reachable but not covered need not be equal to Reachable functions . This is because the reachability analysis is an approximation and thus at runtime some functions may be covered that are not included in the reachability analysis. This is a limitation of our static analysis capabilities.

Function name	source code lines	source lines hit	percentage hit

Files reached

filename	functions hit
/src/llama.cpp/fuzzers/fuzz_json_to_grammar.cpp	1
/src/llama.cpp/vendor/nlohmann/json.hpp	375
/usr/local/bin/../include/c++/v1/__exception/exception.h	2
/src/llama.cpp/common/json-schema-to-grammar.cpp	6
/src/llama.cpp/common/common.cpp	1
/usr/local/bin/../include/c++/v1/stdexcept	1
/src/llama.cpp/common/json-schema-to-grammar.h	1

Fuzzer: fuzz_inference

Call tree

The calltree shows the control flow of the fuzzer. This is overlaid with coverage information to display how much of the potential code a fuzzer can reach is in fact covered at runtime. In the following there is a link to a detailed calltree visualisation as well as a bitmap showing a high-level view of the calltree. For further information about these topics please see the glossary for full calltree and calltree overview

Call tree overview bitmap:

The distribution of callsites in terms of coloring is

Color	Runtime hitcount	Callsite count	Percentage
red	0	8456	94.0%
gold	[1:9]	42	0.46%
yellow	[10:29]	25	0.27%
greenyellow	[30:49]	6	0.06%
lawngreen	50+	461	5.12%
All colors	8990	100

Fuzz blockers

The following nodes represent call sites where fuzz blockers occur.

Amount of callsites blocked	Calltree index	Parent function	Callsite	Largest blocked function
5975	1520	llama_model_load(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector , std::__1::allocator >, std::__1::allocator , std::__1::allocator > > >&, _IO_FILE*, llama_model&, llama_model_params&)	call site: 01520	ggml_backend_alloc_ctx_tensors_from_buft
914	8059	ggml_compute_fp16_to_fp32	call site: 08059	ggml_backend_sched_reserve_size
556	954	llama_model::load_hparams(llama_model_loader&)	call site: 00954	llama_model_rope_type
271	7682	llama_model_load_from_file_impl(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector , std::__1::allocator >, std::__1::allocator , std::__1::allocator > > >&, _IO_FILE*, llama_model_params)	call site: 07682	llama_new_context_with_model
108	7559	llama_file::impl::init_fp(char const*)	call site: 07559	ggml_validate_row_data
87	109	llama_model::llama_model(llama_model_params const&)	call site: 00109	ggml_backend_dev_count
79	7976	ggml_compute_fp32_to_fp16	call site: 07976	quantize_q2_K
58	591	llama_model_loader::llama_model_loader(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector , std::__1::allocator >, std::__1::allocator , std::__1::allocator > > >&, _IO_FILE*, bool, bool, bool, bool, llama_model_kv_override const*, llama_model_tensor_buft_override const*)	call site: 00591	gguf_init_from_file
39	7510	llama_file::impl::tell() const	call site: 07510	__cxa_allocate_exception
30	870	GGUFMeta::GKV ::get_kv(gguf_context const*, int)	call site: 00870	gguf_find_key
26	673	llama_model_loader::llama_model_loader(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector , std::__1::allocator >, std::__1::allocator , std::__1::allocator > > >&, _IO_FILE*, bool, bool, bool, bool, llama_model_kv_override const*, llama_model_tensor_buft_override const*)	call site: 00673	gguf_init_from_file_ptr
19	27	LLVMFuzzerTestOneInput	call site: 00027	llama_max_devices

Runtime coverage analysis

Covered functions

232

Functions that are reachable but not covered

1175

Reachable functions

1521

Percentage of reachable functions covered

22.75%

NB: The sum of covered functions and functions that are reachable but not covered need not be equal to Reachable functions . This is because the reachability analysis is an approximation and thus at runtime some functions may be covered that are not included in the reachability analysis. This is a limitation of our static analysis capabilities.

Function name	source code lines	source lines hit	percentage hit

Files reached

filename	functions hit
/src/llama.cpp/fuzzers/fuzz_inference.cpp	1
/src/llama.cpp/src/llama.cpp	12
/src/llama.cpp/ggml/src/ggml.c	118
/src/llama.cpp/ggml/src/ggml-threading.cpp	2
/src/llama.cpp/common/common.h	15
/src/llama.cpp/common/common.cpp	2
/src/llama.cpp/src/llama-model.cpp	41
/src/llama.cpp/src/llama-impl.cpp	10
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	14
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp	1
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c	1
/src/llama.cpp/ggml/src/./ggml-impl.h	5
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	2
/src/llama.cpp/ggml/src/ggml-backend.cpp	77
/src/llama.cpp/src/llama-vocab.cpp	88
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	33
/src/llama.cpp/src/llama-hparams.cpp	26
/src/llama.cpp/src/llama-adapter.h	2
/src/llama.cpp/src/llama-model-loader.cpp	96
/src/llama.cpp/src/llama-arch.cpp	10
/src/llama.cpp/ggml/src/gguf.cpp	81
/src/llama.cpp/src/llama-mmap.cpp	29
/src/llama.cpp/src/llama-model-loader.h	2
/src/llama.cpp/src/unicode.cpp	38
/usr/local/bin/../include/c++/v1/stdexcept	1
/src/llama.cpp/src/unicode.h	3
/src/llama.cpp/src/llama-arch.h	3
/src/llama.cpp/ggml/src/ggml-impl.h	24
/src/llama.cpp/ggml/src/ggml-alloc.c	33
/src/llama.cpp/ggml/src/ggml-quants.c	84
/src/llama.cpp/src/llama-context.cpp	18
/src/llama.cpp/src/llama-graph.h	6
/src/llama.cpp/src/llama-context.h	2
/src/llama.cpp/src/llama-sampler.cpp	3
/src/llama.cpp/src/llama-memory-recurrent.cpp	4
/src/llama.cpp/src/llama-memory.h	2
/src/llama.cpp/src/llama-memory-hybrid-iswa.cpp	1
/src/llama.cpp/src/llama-kv-cache-iswa.cpp	1
/src/llama.cpp/src/llama-memory-hybrid.cpp	1
/src/llama.cpp/src/llama-kv-cache.cpp	5
/src/llama.cpp/src/llama-kv-cache.h	3
/src/llama.cpp/src/llama-kv-cells.h	3
/src/llama.cpp/src/llama-graph.cpp	11
/src/llama.cpp/src/llama-hparams.h	1
/src/llama.cpp/src/llama-batch.h	5
/src/llama.cpp/src/llama-batch.cpp	5
/src/llama.cpp/ggml/src/ggml-opt.cpp	2

Optimal target analysis

Remaining optimal interesting functions

The following table shows a list of functions that are optimal targets. Optimal targets are identified by finding the functions that in combination, yield a high code coverage.

Func name	Functions filename	Arg count	Args	Function depth	hitcount	instr count	bb count	cyclomatic complexity	Reachable functions	Incoming references	total cyclomatic complexity	Unreached complexity
ggml_backend_cpu_graph_compute(ggml_backend*,ggml_cgraph*)	/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp	2	['N/A', 'N/A']	15	0	63	9	4	1748	0	7726	7579
common_init_from_params(common_params&)	/src/llama.cpp/common/common.cpp	2	['N/A', 'N/A']	19	0	593	149	132	1877	0	25887	3644
common_schema_converter::visit(nlohmann::json_abi_v3_12_0::basic_json ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>const&,std::__1::basic_string ,std::__1::allocator >const&)	/src/llama.cpp/common/json-schema-to-grammar.cpp	4	['N/A', 'N/A', 'N/A', 'N/A']	18	0	2533	646	517	507	5	2846	2540

Implementing fuzzers that target the above functions will improve reachability such that it becomes:

Functions statically reachable by fuzzers

2692 / 5319

Cyclomatic complexity statically reachable by fuzzers

39431 / 59143

All functions overview

If you implement fuzzers for these functions, the status of all functions in the project will be:

Func name	Functions filename	Args	Function call depth	Reached by Fuzzers	Runtime reached by Fuzzers	Combined reached by Fuzzers	Fuzzers runtime hit	Func lines hit %	I Count	BB Count	Cyclomatic complexity	Functions reached	Reached by functions	Accumulated cyclomatic complexity	Undiscovered complexity

This sections provides heuristics that can be used as input to a fuzz engine when running a given fuzz target. The current focus is on providing input that is usable by libFuzzer.

/src/llama.cpp/fuzzers/fuzz_grammar.cpp

Dictionary

Use this with the libFuzzer -dict=DICT.file flag

Fuzzer function priority

Use one of these functions as input to libfuzzer with flag: -focus_function name

-focus_function=['parse_int(char const*)', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)', 'parse_char(char const*)', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)', 'is_word_char(char)', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)::$_0::operator()(unsigned long, unsigned long) const', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)', 'llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector >&, bool)']

/src/llama.cpp/fuzzers/fuzz_apply_template.cpp

Dictionary

Use this with the libFuzzer -dict=DICT.file flag

Fuzzer function priority

Use one of these functions as input to libfuzzer with flag: -focus_function name

-focus_function=['llm_chat_apply_template(llm_chat_template, std::__1::vector > const&, std::__1::basic_string, std::__1::allocator >&, bool)', 'llm_chat_apply_template(llm_chat_template, std::__1::vector > const&, std::__1::basic_string, std::__1::allocator >&, bool)']

/src/llama.cpp/fuzzers/fuzz_load_model.cpp

Dictionary

Use this with the libFuzzer -dict=DICT.file flag

Fuzzer function priority

Use one of these functions as input to libfuzzer with flag: -focus_function name

-focus_function=['llama_model::~llama_model()', 'llama_model::llama_model(llama_model_params const&)', 'ggml_backend_dev_get', 'ggml_init', 'ggml_backend_dev_type', 'ggml_backend_dev_count', 'ggml_aligned_malloc', 'llama_model_load_from_file', 'llama_log_internal_v(ggml_log_level, char const*, __va_list_tag*)']

/src/llama.cpp/fuzzers/fuzz_structured.cpp

Dictionary

Use this with the libFuzzer -dict=DICT.file flag

Fuzzer function priority

Use one of these functions as input to libfuzzer with flag: -focus_function name

-focus_function=['llama_model::~llama_model()', 'llama_model::llama_model(llama_model_params const&)', 'ggml_backend_dev_get', 'ggml_init', 'ggml_backend_dev_type', 'ggml_backend_dev_count', 'ggml_aligned_malloc', 'llama_model_load_from_file', 'llama_log_internal_v(ggml_log_level, char const*, __va_list_tag*)']

/src/llama.cpp/fuzzers/fuzz_json_to_grammar.cpp

Dictionary

Use this with the libFuzzer -dict=DICT.file flag

Fuzzer function priority

Use one of these functions as input to libfuzzer with flag: -focus_function name

-focus_function=['void nlohmann::json_abi_v3_12_0::detail::external_constructor<(nlohmann::json_abi_v3_12_0::detail::value_t)6>::construct, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> >(nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>&, nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::number_unsigned_t)', 'nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::end()', '_ZN8nlohmann16json_abi_v3_12_010basic_jsonINSt3__13mapENS2_6vectorENS2_12basic_stringIcNS2_11char_traitsIcEENS2_9allocatorIcEEEEblmdS8_NS0_14adl_serializerENS4_IhNS8_IhEEEEvEC2IRSA_SA_TnNS2_9enable_ifIXaantsr6detail13is_basic_jsonIT0_EE5valuesr6detail18is_compatible_typeISE_SI_EE5valueEiE4typeELi0EEEOT_', 'std::__1::basic_string, std::__1::allocator > nlohmann::json_abi_v3_12_0::detail::concat, std::__1::allocator >, char const (&) [23], std::__1::basic_string, std::__1::allocator > >(char const (&) [23], std::__1::basic_string, std::__1::allocator >&&)', 'nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::json_value::json_value(std::__1::basic_string, std::__1::allocator > const&)', 'nlohmann::json_abi_v3_12_0::detail::parse_error::parse_error(int, unsigned long, char const*)', 'nlohmann::json_abi_v3_12_0::byte_container_with_subtype > > const& nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::get_ref_impl > > const&, nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> const>(nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void> const&)', 'nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::operator=(nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>)', '_ZN8nlohmann16json_abi_v3_12_06detail12out_of_range6createIDnTnNSt3__19enable_ifIXsr21is_basic_json_contextIT_EE5valueEiE4typeELi0EEES2_iRKNS4_12basic_stringIcNS4_11char_traitsIcEENS4_9allocatorIcEEEES6_', 'nlohmann::json_abi_v3_12_0::basic_json, std::__1::allocator >, bool, long, unsigned long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector >, void>::data::~data()']

/src/llama.cpp/fuzzers/fuzz_inference.cpp

Dictionary

Use this with the libFuzzer -dict=DICT.file flag

Fuzzer function priority

Use one of these functions as input to libfuzzer with flag: -focus_function name

-focus_function=['llama_model_load(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > >&, _IO_FILE*, llama_model&, llama_model_params&)', 'ggml_compute_fp16_to_fp32', 'llama_model::load_hparams(llama_model_loader&)', 'llama_model_load_from_file_impl(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > >&, _IO_FILE*, llama_model_params)', 'llama_file::impl::init_fp(char const*)', 'llama_model::llama_model(llama_model_params const&)', 'ggml_compute_fp32_to_fp16', 'llama_model_loader::llama_model_loader(gguf_context*, void (*)(ggml_tensor*, void*), void*, std::__1::basic_string, std::__1::allocator > const&, std::__1::vector, std::__1::allocator >, std::__1::allocator, std::__1::allocator > > >&, _IO_FILE*, bool, bool, bool, bool, llama_model_kv_override const*, llama_model_tensor_buft_override const*)', 'llama_file::impl::tell() const', 'GGUFMeta::GKV::get_kv(gguf_context const*, int)']

This section shows analysis of runtime coverage data.

For futher technical details on how this section is generated, please see the Glossary .

Complex functions with low coverage

Func name	Function total lines	Lines covered at runtime	percentage covered	Reached by fuzzers
parse_token(llama_vocabconst*,charconst*)	38	15	39.47%	['fuzz_grammar']
llama_model_load_from_file_impl(gguf_context*,void(*)(ggml_tensor*,void*),void*,std::__1::basic_string ,std::__1::allocator >const&,std::__1::vector ,std::__1::allocator >,std::__1::allocator ,std::__1::allocator >>>&,_IO_FILE*,llama_model_params)	177	73	41.24%	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
nlohmann::json_abi_v3_12_0::basic_json ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>::json_value::json_value(nlohmann::json_abi_v3_12_0::detail::value_t)	60	17	28.33%	['fuzz_json_to_grammar']
nlohmann::json_abi_v3_12_0::detail::parser ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>,nlohmann::json_abi_v3_12_0::detail::iterator_input_adapter >::parse(bool,nlohmann::json_abi_v3_12_0::basic_json ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>&)	40	16	40.0%	['fuzz_json_to_grammar']
nlohmann::json_abi_v3_12_0::basic_json ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>::json_value::json_value(nlohmann::json_abi_v3_12_0::detail::value_t)	60	9	15.0%	['fuzz_json_to_grammar']
nlohmann::json_abi_v3_12_0::detail::iter_impl ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>>::set_begin()	33	14	42.42%	['fuzz_json_to_grammar']
nlohmann::json_abi_v3_12_0::detail::iter_impl ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>>::operator*()const	33	14	42.42%	['fuzz_json_to_grammar']
nlohmann::json_abi_v3_12_0::detail::serializer ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>>::dump(nlohmann::json_abi_v3_12_0::basic_json ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>const&,bool,bool,unsignedint,unsignedint)	215	99	46.04%	['fuzz_json_to_grammar']
nlohmann::json_abi_v3_12_0::detail::serializer ,std::__1::allocator >,bool,long,unsignedlong,double,std::__1::allocator,nlohmann::json_abi_v3_12_0::adl_serializer,std::__1::vector >,void>>::dump_escaped(std::__1::basic_string ,std::__1::allocator >const&,bool)	188	94	50.0%	['fuzz_json_to_grammar']
llama_model::load_hparams(llama_model_loader&)	1942	87	4.479%	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']

This section shows which files and directories are considered in this report. The main reason for showing this is fuzz introspector may include more code in the reasoning than is desired. This section helps identify if too many files/directories are included, e.g. third party code, which may be irrelevant for the threat model. In the event too much is included, fuzz introspector supports a configuration file that can exclude data from the report. See the following link for more information on how to create a config file: link

Files in report

Source file	Reached by	Covered by
	[]	[]
/src/llama.cpp/src/models/cohere2-iswa.cpp	[]	[]
/src/llama.cpp/src/models/qwen2moe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/llama-graph.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/baichuan.cpp	[]	[]
/src/llama.cpp/src/models/granite.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-impl.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/pangu-embedded.cpp	[]	[]
/src/llama.cpp/ggml/src/./ggml-impl.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/ggml/src/../include/ggml-cpp.h	[]	[]
/src/llama.cpp/src/models/nemotron.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache.cpp	['fuzz_inference']	[]
/usr/local/bin/../include/c++/v1/__exception/exception.h	['fuzz_json_to_grammar']	[]
/src/llama.cpp/src/models/deepseek2.cpp	[]	[]
/src/llama.cpp/src/llama-context.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/llama-hparams.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/llama-impl.h	[]	[]
/src/llama.cpp/src/llama-model-saver.cpp	[]	[]
/src/llama.cpp/src/llama-arch.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/rwkv7-base.cpp	[]	[]
/src/llama.cpp/common/unicode.cpp	[]	[]
/src/llama.cpp/src/models/codeshell.cpp	[]	[]
/src/llama.cpp/src/models/deci.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-threading.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp	[]	[]
/src/llama.cpp/src/models/hunyuan-moe.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid-iswa.h	[]	[]
/src/llama.cpp/common/sampling.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-iswa.h	[]	[]
/src/llama.cpp/src/models/apertus.cpp	[]	[]
/src/llama.cpp/src/models/chatglm.cpp	[]	[]
/src/llama.cpp/src/llama-adapter.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/models/qwen.cpp	[]	[]
/src/llama.cpp/vendor/nlohmann/json_fwd.hpp	[]	[]
/src/llama.cpp/src/llama-impl.cpp	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/mistral3.cpp	[]	[]
/src/llama.cpp/src/models/internlm2.cpp	[]	[]
/src/llama.cpp/src/models/step35-iswa.cpp	[]	[]
/src/llama.cpp/src/models/paddleocr.cpp	[]	[]
/src/llama.cpp/src/models/t5-enc.cpp	[]	[]
/src/llama.cpp/src/models/qwen2.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cells.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/hunyuan-dense.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/delta-net-base.cpp	[]	[]
/src/llama.cpp/src/models/xverse.cpp	[]	[]
/src/llama.cpp/src/models/ernie4-5.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-dl.h	[]	[]
/src/llama.cpp/src/models/bailingmoe2.cpp	[]	[]
/src/llama.cpp/src/models/minimax-m2.cpp	[]	[]
/src/llama.cpp/src/llama-chat.cpp	['fuzz_apply_template']	['fuzz_apply_template']
/src/llama.cpp/src/models/bailingmoe.cpp	[]	[]
/src/llama.cpp/src/models/command-r.cpp	[]	[]
/src/llama.cpp/src/llama-sampler.h	[]	[]
/src/llama.cpp/src/llama-memory-hybrid-iswa.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/ernie4-5-moe.cpp	[]	[]
/src/llama.cpp/src/llama-hparams.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/gemma4-iswa.cpp	[]	[]
/src/llama.cpp/src/models/llama-iswa.cpp	[]	[]
/src/llama.cpp/src/models/mimo2-iswa.cpp	[]	[]
/src/llama.cpp/src/models/granite-hybrid.cpp	[]	[]
/src/llama.cpp/src/models/olmo.cpp	[]	[]
/src/llama.cpp/src/models/grok.cpp	[]	[]
/src/llama.cpp/common/../vendor/nlohmann/json_fwd.hpp	[]	[]
/src/llama.cpp/common/common.cpp	['fuzz_json_to_grammar', 'fuzz_inference']	['fuzz_json_to_grammar', 'fuzz_inference']
/src/llama.cpp/src/llama-model.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/cogvlm.cpp	[]	[]
/src/llama.cpp/src/models/mpt.cpp	[]	[]
/src/llama.cpp/src/models/olmoe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-dl.cpp	[]	[]
/src/llama.cpp/common/json-schema-to-grammar.cpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/llama-memory-recurrent.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/./llama-graph.h	[]	[]
/src/llama.cpp/src/models/exaone4.cpp	[]	[]
/src/llama.cpp/src/models/qwen3moe.cpp	[]	[]
/src/llama.cpp/src/llama-sampler.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/refact.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_inference.cpp	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/stablelm.cpp	[]	[]
/src/llama.cpp/src/models/minicpm3.cpp	[]	[]
/src/llama.cpp/src/models/qwen3vl.cpp	[]	[]
/src/llama.cpp/src/models/exaone.cpp	[]	[]
/src/llama.cpp/src/models/afmoe.cpp	[]	[]
/src/llama.cpp/src/models/jamba.cpp	[]	[]
/src/llama.cpp/src/unicode.cpp	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_grammar', 'fuzz_inference']
/src/llama.cpp/src/models/chameleon.cpp	[]	[]
/src/llama.cpp/common/reasoning-budget.cpp	[]	[]
/src/llama.cpp/src/models/gemma3.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/repack.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/traits.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/ggml/src/ggml-opt.cpp	['fuzz_inference']	[]
/usr/local/bin/../include/c++/v1/string	[]	[]
/src/llama.cpp/src/llama-context.h	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-cpu/quants.c	[]	[]
/src/llama.cpp/src/models/phi2.cpp	[]	[]
/src/llama.cpp/src/models/qwen3.cpp	[]	[]
/src/llama.cpp/src/models/seed-oss.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/vec.cpp	[]	[]
/src/llama.cpp/src/models/glm4-moe.cpp	[]	[]
/src/llama.cpp/src/llama-batch.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/plm.cpp	[]	[]
/src/llama.cpp/src/models/llada-moe.cpp	[]	[]
/src/llama.cpp/src/models/llama.cpp	[]	[]
/src/llama.cpp/src/models/qwen3vl-moe.cpp	[]	[]
/src/llama.cpp/common/json-schema-to-grammar.h	['fuzz_json_to_grammar']	[]
/usr/local/bin/../include/c++/v1/__exception/exception_ptr.h	[]	[]
/src/llama.cpp/src/models/mamba-base.cpp	[]	[]
/src/llama.cpp/src/models/smallthinker.cpp	[]	[]
/src/llama.cpp/common/common.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/qwen35.cpp	[]	[]
/src/llama.cpp/src/models/bloom.cpp	[]	[]
/src/llama.cpp/src/models/gptneox.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/llama-kv-cache.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/rwkv6.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/ggml/src/ggml.c	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/ggml/src/ggml-cpu/ops.cpp	[]	[]
/src/llama.cpp/src/models/falcon.cpp	[]	[]
/src/llama.cpp/src/models/rwkv7.cpp	[]	[]
/src/llama.cpp/src/models/kimi-linear.cpp	[]	[]
/src/llama.cpp/src/models/plamo.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_grammar.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/fuzzers/fuzz_apply_template.cpp	['fuzz_apply_template']	['fuzz_apply_template']
/src/llama.cpp/src/models/glm4.cpp	[]	[]
/src/llama.cpp/src/llama-io.h	[]	[]
/src/llama.cpp/src/models/wavtokenizer-dec.cpp	[]	[]
/src/llama.cpp/src/llama-grammar.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/jais2.cpp	[]	[]
/src/llama.cpp/src/unicode-data.cpp	[]	[]
/src/llama.cpp/src/models/grovemoe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/simd-gemm.h	[]	[]
/src/llama.cpp/src/models/gemma2-iswa.cpp	[]	[]
/src/llama.cpp/src/models/maincoder.cpp	[]	[]
/src/llama.cpp/src/models/gemma3n-iswa.cpp	[]	[]
/src/llama.cpp/src/models/qwen35moe.cpp	[]	[]
/src/llama.cpp/src/models/bert.cpp	[]	[]
/src/llama.cpp/src/models/llada.cpp	[]	[]
/src/llama.cpp/src/llama-grammar.h	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/arcee.cpp	[]	[]
/src/llama.cpp/src/models/starcoder.cpp	[]	[]
/src/llama.cpp/src/models/lfm2.cpp	[]	[]
/src/llama.cpp/src/llama-vocab.h	[]	[]
/src/llama.cpp/src/llama-graph.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/gemma.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid.h	[]	[]
/src/llama.cpp/src/models/neo-bert.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c	[]	[]
/src/llama.cpp/src/llama-memory-recurrent.h	[]	[]
/src/llama.cpp/src/models/nemotron-h.cpp	[]	[]
/src/llama.cpp/src/models/gemma-embedding.cpp	[]	[]
/src/llama.cpp/src/models/plamo3.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/common/../vendor/nlohmann/json.hpp	[]	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/eurobert.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6-base.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6qwen2.cpp	[]	[]
/src/llama.cpp/common/log.cpp	[]	[]
/src/llama.cpp/src/models/dream.cpp	[]	[]
/src/llama.cpp/src/models/openai-moe-iswa.cpp	[]	[]
/src/llama.cpp/src/llama-adapter.cpp	[]	[]
/src/llama.cpp/src/llama-batch.h	['fuzz_inference']	[]
/src/llama.cpp/src/llama-memory.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/phi3.cpp	[]	[]
/src/llama.cpp/src/models/dbrx.cpp	[]	[]
/src/llama.cpp/src/models/qwen3next.cpp	[]	[]
/src/llama.cpp/src/models/olmo2.cpp	[]	[]
/src/llama.cpp/src/llama-vocab.cpp	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/mamba.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/common.h	[]	[]
/src/llama.cpp/src/models/smollm3.cpp	[]	[]
/src/llama.cpp/src/llama-memory.cpp	[]	[]
/src/llama.cpp/src/llama-model.h	[]	[]
/src/llama.cpp/fuzzers/fuzz_structured.cpp	['fuzz_structured']	['fuzz_structured']
/src/llama.cpp/src/models/t5-dec.cpp	[]	[]
/src/llama.cpp/src/../include/llama-cpp.h	[]	[]
/src/llama.cpp/src/llama-model-loader.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/models.h	[]	[]
/src/llama.cpp/src/models/gpt2.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-alloc.c	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/models/deepseek.cpp	[]	[]
/src/llama.cpp/src/models/falcon-h1.cpp	[]	[]
/src/llama.cpp/src/models/openelm.cpp	[]	[]
/src/llama.cpp/src/models/modern-bert.cpp	[]	[]
/src/llama.cpp/src/models/plamo2.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/starcoder2.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-quants.c	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/qwen2vl.cpp	[]	[]
/src/llama.cpp/src/unicode.h	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/models/dots1.cpp	[]	[]
/src/llama.cpp/src/models/orion.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_json_to_grammar.cpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/bitnet.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_load_model.cpp	['fuzz_load_model']	['fuzz_load_model']
/src/llama.cpp/src/llama.cpp	['fuzz_apply_template', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_apply_template', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/arctic.cpp	[]	[]
/src/llama.cpp/src/models/jais.cpp	[]	[]
/src/llama.cpp/common/unicode.h	[]	[]
/src/llama.cpp/src/llama-arch.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h	[]	[]
/src/llama.cpp/src/models/rnd1.cpp	[]	[]
/src/llama.cpp/ggml/src/gguf.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/common/sampling.h	[]	[]
/src/llama.cpp/src/models/exaone-moe.cpp	[]	[]
/usr/local/bin/../include/c++/v1/stdexcept	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_json_to_grammar', 'fuzz_inference']	[]
/src/llama.cpp/src/llama-model-loader.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/llama-io.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/traits.h	[]	[]
/usr/local/bin/../include/c++/v1/istream	[]	[]
/src/llama.cpp/src/llama-kv-cache-iswa.cpp	['fuzz_inference']	[]
/src/llama.cpp/vendor/nlohmann/json.hpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/arwkv7.cpp	[]	[]
/src/llama.cpp/src/llama-mmap.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']

Directories in report

Directory
/src/llama.cpp/src/
/src//src/models/
/src/llama.cpp/common/../vendor/nlohmann/
/src/llama.cpp/ggml/src/ggml-cpu/llamafile/
/usr/local/bin/../include/c++/v1/
/src/llama.cpp/src/../include/
/src/llama.cpp/fuzzers/
/src/llama.cpp/ggml/src/./
/src/llama.cpp/ggml/src/ggml-cpu/
/src//src/
/src/llama.cpp/vendor/nlohmann/
/src/llama.cpp/ggml/src/
/src/llama.cpp/ggml/src/../include/
/src/llama.cpp/src/./
/src/llama.cpp/src/models/
/usr/local/bin/../include/c++/v1/__exception/
/src/llama.cpp/common/
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/