High level conclusions

Fuzzer fuzz_structured is blocked:

The runtime code coverage of fuzz_structured covers 9.922% 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 18.83% 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 18.35% 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 25.94% of cyclomatic complexity.

Fuzzers reach 21.11% of all functions.

Reachability and coverage overview

Functions statically reachable by fuzzers

1318 / 6243

Cyclomatic complexity statically reachable by fuzzers

14479 / 55811

Runtime code coverage of functions

1054 / 6243

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	264	74.3%
gold	[1:9]	30	8.45%
yellow	[10:29]	14	3.94%
greenyellow	[30:49]	4	1.12%
lawngreen	50+	43	12.1%
All colors	355	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
213	64	parse_int(char const*)	call site: 00064	ggml_abort
11	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	44	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00044	__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	299	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: 00299	__cxa_allocate_exception
4	312	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00312	__cxa_allocate_exception
4	322	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00322	__cxa_allocate_exception
4	332	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00332	__cxa_allocate_exception
1	330	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00330

Runtime coverage analysis

Covered functions

18

Functions that are reachable but not covered

169

Reachable functions

207

Percentage of reachable functions covered

18.36%

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	55
/src/llama.cpp/ggml/src/ggml.c	1
/src/llama.cpp/src/llama-impl.cpp	3
/src/llama.cpp/src/unicode.cpp	10
/usr/local/bin/../include/c++/v1/stdexcept	1
/src/llama.cpp/src/unicode.h	1

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	1100	83.1%
gold	[1:9]	174	13.1%
yellow	[10:29]	27	2.04%
greenyellow	[30:49]	3	0.22%
lawngreen	50+	19	1.43%
All colors	1323	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
285	705	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_params&)	call site: 00705	__cxa_allocate_exception
163	1127	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_params&)	call site: 01127	__cxa_allocate_exception
131	991	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_params&)	call site: 00991	ggml_backend_dev_get
126	494	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: 00494	gguf_init_from_file
73	624	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: 00624	_ZN8GGUFMeta3GKVIjE12try_overrideIjEENSt3__19enable_ifIXaantsr3std7is_sameIT_bEE5valuesr3std11is_integralIS5_EE5valueEbE4typeERS5_PK23llama_model_kv_override
63	67	get_reg()	call site: 00067	ggml_backend_load_all
61	329	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00329	ggml_new_tensor_1d
45	403	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: 00403	_ZN8GGUFMeta3GKVINSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEE12try_overrideIS7_EENS1_9enable_ifIXsr3std7is_sameIT_S7_EE5valueEbE4typeERS7_PK23llama_model_kv_override
34	458	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: 00458	gguf_find_tensor
15	284	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00284	ggml_abort
8	216	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00216	ggml_log_internal
6	182	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00182	ggml_log_internal

Runtime coverage analysis

Covered functions

115

Functions that are reachable but not covered

629

Reachable functions

775

Percentage of reachable functions covered

18.84%

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	9
/src/llama.cpp/ggml/src/ggml.c	28
/src/llama.cpp/ggml/src/ggml-threading.cpp	2
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	18
/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	10
/src/llama.cpp/ggml/src/ggml-backend-dl.cpp	3
/src/llama.cpp/src/llama-impl.cpp	9
/src/llama.cpp/src/llama-model-loader.cpp	44
/src/llama.cpp/src/llama-arch.cpp	5
/src/llama.cpp/ggml/src/gguf.cpp	81
/src/llama.cpp/src/llama-mmap.cpp	6
/src/llama.cpp/src/llama-model-loader.h	2
/src/llama.cpp/src/llama-model.cpp	22
/src/llama.cpp/src/models/models.h	130
/src/llama.cpp/src/llama-vocab.cpp	7
/src/llama.cpp/src/llama-vocab.h	1
/src/llama.cpp/src/llama-arch.h	1
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	3
/src/llama.cpp/src/llama-hparams.cpp	16
/src/llama.cpp/ggml/src/ggml-quants.c	4

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	1182	89.0%
gold	[1:9]	119	8.96%
yellow	[10:29]	6	0.45%
greenyellow	[30:49]	2	0.15%
lawngreen	50+	19	1.43%
All colors	1328	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
297	404	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: 00404	gguf_init_from_file
285	709	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_params&)	call site: 00709	__cxa_allocate_exception
191	203	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00203	ggml_new_tensor_1d
163	1131	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_params&)	call site: 01131	__cxa_allocate_exception
131	995	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_params&)	call site: 00995	ggml_backend_dev_get
63	67	get_reg()	call site: 00067	ggml_backend_load_all
9	9	ggml_log_internal_v	call site: 00009	ggml_abort
7	185	gguf_reader::read_raw(void*, unsigned long) const	call site: 00185	ggml_log_internal
6	702	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_params&)	call site: 00702
4	1304	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: 01304	llama_free_model
3	161	ggml_fopen	call site: 00161	ggml_log_internal
2	1295	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_params&)	call site: 01295	ggml_time_us

Runtime coverage analysis

Covered functions

62

Functions that are reachable but not covered

699

Reachable functions

776

Percentage of reachable functions covered

9.92%

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	9
/src/llama.cpp/ggml/src/ggml.c	28
/src/llama.cpp/ggml/src/ggml-threading.cpp	2
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	18
/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	10
/src/llama.cpp/ggml/src/ggml-backend-dl.cpp	3
/src/llama.cpp/src/llama-impl.cpp	9
/src/llama.cpp/src/llama-model-loader.cpp	44
/src/llama.cpp/src/llama-arch.cpp	5
/src/llama.cpp/ggml/src/gguf.cpp	81
/src/llama.cpp/src/llama-mmap.cpp	6
/src/llama.cpp/src/llama-model-loader.h	2
/src/llama.cpp/src/llama-model.cpp	22
/src/llama.cpp/src/models/models.h	130
/src/llama.cpp/src/llama-vocab.cpp	7
/src/llama.cpp/src/llama-vocab.h	1
/src/llama.cpp/src/llama-arch.h	1
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	3
/src/llama.cpp/src/llama-hparams.cpp	16
/src/llama.cpp/ggml/src/ggml-quants.c	4

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	2.08%
gold	[1:9]	6	6.25%
yellow	[10:29]	16	16.6%
greenyellow	[30:49]	5	5.20%
lawngreen	50+	67	69.7%
All colors	96	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	80	llm_chat_apply_template(llm_chat_template, std::__1::vector > const&, std::__1::basic_string , std::__1::allocator >&, bool)	call site: 00080
1	84	llm_chat_apply_template(llm_chat_template, std::__1::vector > const&, std::__1::basic_string , std::__1::allocator >&, bool)	call site: 00084

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_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	2374	78.7%
gold	[1:9]	180	5.96%
yellow	[10:29]	30	0.99%
greenyellow	[30:49]	10	0.33%
lawngreen	50+	422	13.9%
All colors	3016	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
978	2021	ggml_compute_fp16_to_fp32	call site: 02021	ggml_backend_sched_reserve_size
579	1328	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: 01328	llama_new_context_with_model
158	1160	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_params&)	call site: 01160	__cxa_allocate_exception
94	1019	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_params&)	call site: 01019	ggml_backend_dev_count
79	1938	ggml_compute_fp32_to_fp16	call site: 01938	quantize_q2_K
63	67	get_reg()	call site: 00067	ggml_backend_load_all
44	947	llama_model_bailingmoe::llama_model_bailingmoe(llama_model_params const&)	call site: 00947
43	555	llama_get_list_splits(std::__1::basic_string , std::__1::allocator > const&, int, int)	call site: 00555	gguf_init_from_file
26	622	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: 00622	gguf_init_from_file_ptr
25	131	LLVMFuzzerTestOneInput	call site: 00131	llama_max_devices
16	919	llama_model_exaone::llama_model_exaone(llama_model_params const&)	call site: 00919
14	437	_ZN8GGUFMeta3GKVINSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEE12try_overrideIS7_EENS1_9enable_ifIXsr3std7is_sameIT_S7_EE5valueEbE4typeERS7_PK23llama_model_kv_override	call site: 00437	__cxa_allocate_exception

Runtime coverage analysis

Covered functions

313

Functions that are reachable but not covered

918

Reachable functions

1381

Percentage of reachable functions covered

33.53%

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_inference.cpp	1
/src/llama.cpp/src/llama.cpp	11
/src/llama.cpp/ggml/src/ggml.c	105
/src/llama.cpp/ggml/src/ggml-threading.cpp	2
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	20
/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	69
/src/llama.cpp/ggml/src/ggml-backend-dl.cpp	3
/src/llama.cpp/common/common.h	22
/src/llama.cpp/common/common.cpp	2
/src/llama.cpp/src/llama-model.cpp	33
/src/llama.cpp/src/llama-impl.cpp	9
/src/llama.cpp/src/llama-model-loader.cpp	44
/src/llama.cpp/src/llama-arch.cpp	8
/src/llama.cpp/ggml/src/gguf.cpp	81
/src/llama.cpp/src/llama-mmap.cpp	6
/src/llama.cpp/src/llama-model-loader.h	2
/src/llama.cpp/src/models/models.h	130
/src/llama.cpp/src/llama-vocab.cpp	7
/src/llama.cpp/src/llama-vocab.h	1
/src/llama.cpp/src/llama-arch.h	1
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	38
/src/llama.cpp/src/llama-hparams.cpp	22
/src/llama.cpp/src/llama-context.cpp	21
/src/llama.cpp/src/llama-cparams.h	4
/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-kv-cache-dsa.cpp	1
/src/llama.cpp/src/llama-memory.h	2
/src/llama.cpp/src/llama-memory-recurrent.cpp	4
/src/llama.cpp/ggml/src/ggml-alloc.c	33
/src/llama.cpp/src/llama-memory-hybrid-iswa.cpp	1
/src/llama.cpp/src/llama-kv-cache-iswa.cpp	3
/src/llama.cpp/src/llama-memory-hybrid.cpp	1
/src/llama.cpp/src/llama-kv-cache.cpp	6
/src/llama.cpp/src/llama-kv-cache.h	3
/src/llama.cpp/src/llama-kv-cells.h	4
/src/llama.cpp/ggml/src/ggml-impl.h	25
/src/llama.cpp/ggml/src/ggml-quants.c	78
/src/llama.cpp/src/llama-adapter.h	1
/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

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]	8	0.94%
greenyellow	[30:49]	2	0.23%
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

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	1775	0	8505	8342
common_init_from_params(common_params&,bool)	/src/llama.cpp/common/common.cpp	3	['N/A', 'N/A', 'bool']	19	0	611	156	135	1893	0	14371	4179
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	2519	643	515	507	5	2842	2536

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

Functions statically reachable by fuzzers

2719 / 6243

Cyclomatic complexity statically reachable by fuzzers

28967 / 55811

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)', '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)']

/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_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_params&)', '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_params&)', '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_params&)', '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_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*)', 'get_reg()', 'gguf_init_from_reader(gguf_reader const&, gguf_init_params)', '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_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*)', 'gguf_init_from_reader(gguf_reader const&, gguf_init_params)']

/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_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_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_params&)', 'gguf_init_from_reader(gguf_reader const&, gguf_init_params)', '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_params&)', '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_params&)', 'get_reg()', 'ggml_log_internal_v', 'gguf_reader::read_raw(void*, unsigned long) const', '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_params&)', '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)']

/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_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=['ggml_compute_fp16_to_fp32', '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_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_params&)', '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_params&)', 'ggml_compute_fp32_to_fp16', 'get_reg()', 'llama_model_bailingmoe::llama_model_bailingmoe(llama_model_params const&)', 'llama_get_list_splits(std::__1::basic_string, std::__1::allocator > const&, int, int)', '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*)', 'LLVMFuzzerTestOneInput']

/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()']

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(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&)	47	25	53.19%	['fuzz_inference', 'fuzz_structured', 'fuzz_load_model']
llama_model_mapping(llm_arch,llama_model_paramsconst&)	266	142	53.38%	['fuzz_inference', 'fuzz_structured', 'fuzz_load_model']
llama_prepare_model_devices(llama_model_paramsconst&,llama_model*)	129	28	21.70%	['fuzz_inference', 'fuzz_structured', 'fuzz_load_model']
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']

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/llama-impl.h	[]	[]
/src/llama.cpp/src/models/gemma2.cpp	[]	[]
/src/llama.cpp/src/models/plamo3.cpp	[]	[]
/src/llama.cpp/src/models/exaone.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h	[]	[]
/src/llama.cpp/src/models/glm4.cpp	[]	[]
/src/llama.cpp/common/json-schema-to-grammar.cpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/llama-context.cpp	['fuzz_inference']	[]
/usr/local/bin/../include/c++/v1/string	[]	[]
/src/llama.cpp/src/models/deepseek32.cpp	[]	[]
/src/llama.cpp/src/./llama-arch.h	[]	['fuzz_inference']
/src/llama.cpp/src/models/hunyuan-vl.cpp	[]	[]
/src/llama.cpp/src/models/exaone-moe.cpp	[]	[]
/src/llama.cpp/src/models/cohere2moe.cpp	[]	[]
/src/llama.cpp/src/models/bert.cpp	[]	[]
/src/llama.cpp/src/models/refact.cpp	[]	[]
/src/llama.cpp/src/models/qwen.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6qwen2.cpp	[]	[]
/src/llama.cpp/src/models/command-r.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/traits.h	[]	[]
/src/llama.cpp/src/models/baichuan.cpp	[]	[]
/src/llama.cpp/src/models/orion.cpp	[]	[]
/usr/local/bin/../include/c++/v1/__exception/exception_ptr.h	[]	[]
/src/llama.cpp/src/./llama-graph.h	[]	[]
/src/llama.cpp/src/models/arwkv7.cpp	[]	[]
/src/llama.cpp/src/models/qwen3vlmoe.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid.h	[]	[]
/src/llama.cpp/src/llama-memory-recurrent.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/starcoder.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp	[]	[]
/src/llama.cpp/src/models/ernie4-5-moe.cpp	[]	[]
/src/llama.cpp/common/common.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/qwen35.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/src/models/qwen3next.cpp	[]	[]
/src/llama.cpp/common/sampling.cpp	[]	[]
/src/llama.cpp/src/models/modern-bert.cpp	[]	[]
/src/llama.cpp/src/models/codeshell.cpp	[]	[]
/src/llama.cpp/src/models/granite-hybrid.cpp	[]	[]
/src/llama.cpp/src/llama-memory.cpp	[]	[]
/src/llama.cpp/src/models/lfm2moe.cpp	[]	[]
/src/llama.cpp/common/../vendor/nlohmann/json.hpp	[]	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/plamo2.cpp	[]	[]
/src/llama.cpp/src/models/gemma3n.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache.cpp	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/gguf.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/ggml/src/ggml-cpu/simd-gemm.h	[]	[]
/src/llama.cpp/src/models/jais2.cpp	[]	[]
/src/llama.cpp/src/models/qwen2moe.cpp	[]	[]
/src/llama.cpp/src/models/ernie4-5.cpp	[]	[]
/src/llama.cpp/src/models/cohere2.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-dl.h	[]	[]
/src/llama.cpp/src/llama-model-saver.cpp	[]	[]
/src/llama.cpp/src/models/deepseek2ocr.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/repack.cpp	[]	[]
/src/llama.cpp/src/models/afmoe.cpp	[]	[]
/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/llamafile/sgemm.cpp	[]	[]
/src/llama.cpp/src/../include/llama-cpp.h	[]	[]
/src/llama.cpp/src/models/gemma3.cpp	[]	[]
/src/llama.cpp/src/models/t5encoder.cpp	[]	[]
/src/llama.cpp/src/llama.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_apply_template', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_apply_template', 'fuzz_inference']
/src/llama.cpp/src/llama-graph.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/arctic.cpp	[]	[]
/src/llama.cpp/src/models/llama-embed.cpp	[]	[]
/src/llama.cpp/src/models/step35.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6-base.cpp	[]	[]
/src/llama.cpp/common/common.cpp	['fuzz_inference', 'fuzz_json_to_grammar']	['fuzz_inference', 'fuzz_json_to_grammar']
/src/llama.cpp/src/unicode.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/ggml/src/ggml-backend-dl.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/models/jina-bert-v2.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_load_model.cpp	['fuzz_load_model']	['fuzz_load_model']
/src/llama.cpp/src/llama-sampler.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/llama-model-loader.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/./llama-batch.h	[]	[]
/src/llama.cpp/src/llama-sampler.h	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/common.h	[]	[]
/src/llama.cpp/src/llama-graph.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/granite.cpp	[]	[]
/src/llama.cpp/src/llama-grammar.h	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/grok.cpp	[]	[]
/src/llama.cpp/src/models/deepseek.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/models/rnd1.cpp	[]	[]
/src/llama.cpp/src/models/llada.cpp	[]	[]
/src/llama.cpp/src/models/minicpm3.cpp	[]	[]
/src/llama.cpp/src/models/stablelm.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/mpt.cpp	[]	[]
/src/llama.cpp/ggml/src/../include/ggml-cpp.h	[]	[]
/src/llama.cpp/src/unicode.h	['fuzz_grammar']	[]
/src/llama.cpp/src/llama-model-loader.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/llama-chat.cpp	['fuzz_apply_template']	['fuzz_apply_template']
/src/llama.cpp/src/llama-mmap.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/llama-model.h	[]	[]
/src/llama.cpp/src/models/mimo2.cpp	[]	[]
/src/llama.cpp/src/models/minimax-m2.cpp	[]	[]
/src/llama.cpp/src/llama-model.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_inference']
/src/llama.cpp/src/models/plm.cpp	[]	[]
/src/llama.cpp/src/llama-adapter.cpp	[]	[]
/src/llama.cpp/src/models/openai-moe.cpp	[]	[]
/src/llama.cpp/src/llama-memory-recurrent.h	[]	[]
/src/llama.cpp/src/models/wavtokenizer-dec.cpp	[]	[]
/src/llama.cpp/src/llama-vocab.cpp	['fuzz_grammar', 'fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_grammar', 'fuzz_load_model', 'fuzz_inference']
/src/llama.cpp/src/llama-grammar.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/xverse.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-opt.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/jina-bert-v3.cpp	[]	[]
/src/llama.cpp/src/models/eagle3.cpp	[]	[]
/src/llama.cpp/src/models/dots1.cpp	[]	[]
/src/llama.cpp/src/models/falcon-h1.cpp	[]	[]
/src/llama.cpp/src/models/plamo.cpp	[]	[]
/src/llama.cpp/src/models/exaone4.cpp	[]	[]
/src/llama.cpp/src/models/smollm3.cpp	[]	[]
/src/llama.cpp/src/models/arcee.cpp	[]	[]
/src/llama.cpp/src/models/cogvlm.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-iswa.h	[]	[]
/src/llama.cpp/vendor/nlohmann/json_fwd.hpp	[]	[]
/src/llama.cpp/src/models/kimi-linear.cpp	[]	[]
/src/llama.cpp/src/llama-batch.cpp	['fuzz_inference']	[]
/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/bailingmoe2.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/mellum.cpp	[]	[]
/src/llama.cpp/src/models/nemotron-h.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/models/starcoder2.cpp	[]	[]
/src/llama.cpp/src/llama-arch.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/src/llama.cpp/src/models/delta-net-base.cpp	[]	[]
/src/llama.cpp/src/models/olmoe.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/models/mamba2.cpp	[]	[]
/src/llama.cpp/src/models/qwen2.cpp	[]	[]
/src/llama.cpp/src/llama-batch.h	['fuzz_inference']	[]
/src/llama.cpp/common/../vendor/nlohmann/json_fwd.hpp	[]	[]
/src/llama.cpp/src/models/granite-moe.cpp	[]	[]
/src/llama.cpp/src/models/phimoe.cpp	[]	[]
/src/llama.cpp/common/sampling.h	[]	[]
/src/llama.cpp/src/models/gemma4.cpp	[]	[]
/src/llama.cpp/src/models/qwen3moe.cpp	[]	[]
/src/llama.cpp/src/models/rwkv7-base.cpp	[]	[]
/src/llama.cpp/src/models/hunyuan-dense.cpp	[]	[]
/src/llama.cpp/src/models/seed-oss.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/ops.cpp	[]	[]
/src/llama.cpp/src/models/bloom.cpp	[]	[]
/usr/local/bin/../include/c++/v1/__exception/exception.h	['fuzz_json_to_grammar']	[]
/src/llama.cpp/ggml/src/ggml-cpu/traits.cpp	[]	[]
/src/llama.cpp/vendor/nlohmann/json.hpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/glm4-moe.cpp	[]	[]
/src/llama.cpp/src/models/hunyuan-moe.cpp	[]	[]
/src/llama.cpp/src/llama-hparams.h	['fuzz_inference']	[]
/src/llama.cpp/common/log.cpp	[]	[]
/src/llama.cpp/common/unicode.cpp	[]	[]
/src/llama.cpp/src/models/deepseek2.cpp	[]	[]
/src/llama.cpp/src/models/phi3.cpp	[]	[]
/src/llama.cpp/src/models/qwen35moe.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-dsa.cpp	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp	[]	[]
/src/llama.cpp/src/models/maincoder.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-alloc.c	['fuzz_inference']	[]
/src/llama.cpp/src/models/phi2.cpp	[]	[]
/usr/local/bin/../include/c++/v1/initializer_list	[]	[]
/src/llama.cpp/src/models/nemotron-h-moe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']
/usr/local/bin/../include/c++/v1/stdexcept	['fuzz_grammar', 'fuzz_json_to_grammar']	[]
/src/llama.cpp/src/models/bailingmoe.cpp	[]	[]
/src/llama.cpp/src/llama-context.h	['fuzz_inference']	[]
/src/llama.cpp/src/llama-hparams.cpp	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/models/smallthinker.cpp	[]	[]
/src/llama.cpp/src/models/nomic-bert-moe.cpp	[]	[]
/src/llama.cpp/src/models/jamba.cpp	[]	[]
/src/llama.cpp/src/unicode-data.cpp	[]	[]
/src/llama.cpp/src/llama-ext.h	[]	[]
/src/llama.cpp/src/llama-io.cpp	[]	[]
/src/llama.cpp/src/models/lfm2.cpp	[]	[]
/src/llama.cpp/src/models/models.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/llama.cpp	[]	[]
/src/llama.cpp/src/models/apertus.cpp	[]	[]
/src/llama.cpp/src/models/t5.cpp	[]	[]
/src/llama.cpp/src/models/talkie.cpp	[]	[]
/src/llama.cpp/common/fit.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/quants.c	[]	[]
/src/llama.cpp/ggml/src/./ggml-impl.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/gemma-embedding.cpp	[]	[]
/src/llama.cpp/src/models/gptneox.cpp	[]	[]
/src/llama.cpp/build/common/build-info.cpp	[]	[]
/src/llama.cpp/src/models/openelm.cpp	[]	[]
/src/llama.cpp/src/models/gpt2.cpp	[]	[]
/src/llama.cpp/src/models/neo-bert.cpp	[]	[]
/src/llama.cpp/src/models/qwen3vl.cpp	[]	[]
/src/llama.cpp/src/models/rwkv7.cpp	[]	[]
/src/llama.cpp/src/models/eurobert.cpp	[]	[]
/src/llama.cpp/src/models/nemotron.cpp	[]	[]
/src/llama.cpp/src/models/qwen2vl.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/vec.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_inference.cpp	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp	[]	[]
/src/llama.cpp/src/models/olmo.cpp	[]	[]
/src/llama.cpp/src/llama-adapter.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/gemma4-assistant.cpp	[]	[]
/src/llama.cpp/src/models/chatglm.cpp	[]	[]
/src/llama.cpp/common/../src/llama-ext.h	[]	[]
/src/llama.cpp/common/json-schema-to-grammar.h	['fuzz_json_to_grammar']	[]
/src/llama.cpp/src/llama-kv-cache-dsa.h	[]	[]
/src/llama.cpp/fuzzers/fuzz_grammar.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/mamba.cpp	[]	[]
/src/llama.cpp/common/reasoning-budget.cpp	[]	[]
/src/llama.cpp/src/models/paddleocr.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/src/models/nomic-bert.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_json_to_grammar.cpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/internlm2.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/mistral3.cpp	[]	[]
/src/llama.cpp/src/models/qwen3.cpp	[]	[]
/src/llama.cpp/src/models/falcon.cpp	[]	[]
/src/llama.cpp/src/llama-io.h	[]	[]
/src/llama.cpp/common/unicode.h	[]	[]
/src/llama.cpp/src/models/rwkv6.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cells.h	['fuzz_inference']	['fuzz_inference']
/usr/local/bin/../include/c++/v1/istream	[]	[]
/src/llama.cpp/src/models/mamba-base.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_apply_template.cpp	['fuzz_apply_template']	['fuzz_apply_template']
/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/glm-dsa.cpp	[]	[]
/src/llama.cpp/src/models/mistral4.cpp	[]	[]
/src/llama.cpp/src/models/olmo2.cpp	[]	[]
/src/llama.cpp/src/models/bitnet.cpp	[]	[]
/src/llama.cpp/src/models/gemma.cpp	[]	[]
/src/llama.cpp/src/models/grovemoe.cpp	[]	[]
/src/llama.cpp/src/models/jais.cpp	[]	[]
/src/llama.cpp/src/llama-memory.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/minicpm.cpp	[]	[]
/src/llama.cpp/src/models/deci.cpp	[]	[]
/src/llama.cpp/src/models/pangu-embed.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_structured.cpp	['fuzz_structured']	['fuzz_structured']
/src/llama.cpp/src/llama-memory-hybrid-iswa.h	[]	[]
/src/llama.cpp/src/models/llama4.cpp	[]	[]
/src/llama.cpp/src/models/llada-moe.cpp	[]	[]
/src/llama.cpp/src/models/dbrx.cpp	[]	[]
/src/llama.cpp/src/llama-cparams.h	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-impl.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/dream.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid-iswa.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/chameleon.cpp	[]	[]
/src/llama.cpp/src/llama-arch.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/llama-vocab.h	['fuzz_load_model', 'fuzz_structured', 'fuzz_inference']	[]
/src/llama.cpp/src/llama-kv-cache-iswa.cpp	['fuzz_inference']	[]

Directories in report

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