High level conclusions

Fuzzer fuzz_structured is blocked:

The runtime code coverage of fuzz_structured covers 9.948% 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 18.44% 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 25.12% of cyclomatic complexity.

Fuzzers reach 20.63% of all functions.

Reachability and coverage overview

Functions statically reachable by fuzzers

1337 / 6479

Cyclomatic complexity statically reachable by fuzzers

14266 / 56776

Runtime code coverage of functions

1085 / 6479

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	265	74.2%
gold	[1:9]	32	8.96%
yellow	[10:29]	16	4.48%
greenyellow	[30:49]	5	1.40%
lawngreen	50+	39	10.9%
All colors	357	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
215	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	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	301	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: 00301	__cxa_allocate_exception
4	314	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00314	__cxa_allocate_exception
4	324	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00324	__cxa_allocate_exception
4	334	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00334	__cxa_allocate_exception
4	344	llama_grammar_parser::parse_rule(char const*)	call site: 00344	__cxa_allocate_exception
1	332	llama_grammar_parser::parse_sequence(char const*, std::__1::basic_string , std::__1::allocator > const&, std::__1::vector >&, bool)	call site: 00332

Runtime coverage analysis

Covered functions

18

Functions that are reachable but not covered

168

Reachable functions

206

Percentage of reachable functions covered

18.45%

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_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	1302	89.7%
gold	[1:9]	118	8.13%
yellow	[10:29]	7	0.48%
greenyellow	[30:49]	2	0.13%
lawngreen	50+	21	1.44%
All colors	1450	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	408	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: 00408	gguf_init_from_file
292	712	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: 00712	__cxa_allocate_exception
247	1005	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: 01005	ggml_backend_dev_get
192	206	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00206	ggml_new_tensor_1d
159	1257	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: 01257	__cxa_allocate_exception
63	70	get_reg()	call site: 00070	ggml_backend_load_all
9	9	ggml_log_internal_v	call site: 00009	ggml_abort
7	188	gguf_reader::read_raw(void*, unsigned long) const	call site: 00188	ggml_log_internal
5	706	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: 00706	llama_ftype_name
4	1426	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: 01426	llama_free_model
3	164	ggml_fopen	call site: 00164	ggml_log_internal
2	198	gguf_init_from_reader(gguf_reader const&, gguf_init_params)	call site: 00198	ggml_log_internal

Runtime coverage analysis

Covered functions

63

Functions that are reachable but not covered

706

Reachable functions

784

Percentage of reachable functions covered

9.95%

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	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	6
/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	133
/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_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	2512	78.8%
gold	[1:9]	211	6.62%
yellow	[10:29]	41	1.28%
greenyellow	[30:49]	2	0.06%
lawngreen	50+	419	13.1%
All colors	3185	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
1008	2160	ggml_compute_fp16_to_fp32	call site: 02160	ggml_backend_sched_reserve_size
592	1450	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: 01450	llama_new_context_with_model
210	1029	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: 01029	ggml_backend_dev_count
154	1286	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: 01286	__cxa_allocate_exception
83	2073	ggml_compute_fp32_to_fp16	call site: 02073	quantize_q2_K
63	70	get_reg()	call site: 00070	ggml_backend_load_all
43	559	llama_get_list_splits(std::__1::basic_string , std::__1::allocator > const&, int, int)	call site: 00559	gguf_init_from_file
26	626	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: 00626	gguf_init_from_file_ptr
25	134	LLVMFuzzerTestOneInput	call site: 00134	llama_max_devices
14	441	_ZN8GGUFMeta3GKVINSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEE12try_overrideIS7_EENS1_9enable_ifIXsr3std7is_sameIT_S7_EE5valueEbE4typeERS7_PK23llama_model_kv_override	call site: 00441	__cxa_allocate_exception
14	985	llama_model_lfm2::llama_model_lfm2(llama_model_params const&)	call site: 00985
14	1262	ggml_backend_dev_type	call site: 01262	ggml_backend_dev_backend_reg

Runtime coverage analysis

Covered functions

328

Functions that are reachable but not covered

924

Reachable functions

1415

Percentage of reachable functions covered

34.7%

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	104
/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	6
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	2
/src/llama.cpp/ggml/src/ggml-backend.cpp	70
/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	133
/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	24
/src/llama.cpp/src/llama-cparams.h	4
/src/llama.cpp/src/llama-graph.h	7
/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	4
/src/llama.cpp/src/llama-memory-hybrid.cpp	1
/src/llama.cpp/src/llama-kv-cache.cpp	8
/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	80
/src/llama.cpp/src/llama-kv-cache-dsv4.cpp	7
/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_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]	5	5.20%
yellow	[10:29]	16	16.6%
greenyellow	[30:49]	5	5.20%
lawngreen	50+	68	70.8%
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_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	957	66.2%
gold	[1:9]	38	2.62%
yellow	[10:29]	31	2.14%
greenyellow	[30:49]	5	0.34%
lawngreen	50+	414	28.6%
All colors	1445	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
269	725	llama_model_base::llama_model_base(llama_model_params const&)	call site: 00725	__cxa_allocate_exception
210	1001	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: 01001	ggml_backend_dev_count
154	1258	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: 01258	__cxa_allocate_exception
63	70	get_reg()	call site: 00070	ggml_backend_load_all
58	516	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: 00516	gguf_init_from_file
26	598	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: 00598	gguf_init_from_file_ptr
14	1234	ggml_backend_dev_type	call site: 01234	ggml_backend_dev_backend_reg
13	1217	ggml_backend_dev_get	call site: 01217	ggml_backend_meta_device
10	587	GGUFMeta::GKV_Base_Type ::getter(gguf_context const*, int)	call site: 00587	ggml_abort
9	576	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: 00576	_ZN8GGUFMeta3GKVIiE12try_overrideIiEENSt3__19enable_ifIXaantsr3std7is_sameIT_bEE5valuesr3std11is_integralIS5_EE5valueEbE4typeERS5_PK23llama_model_kv_override
8	419	GGUFMeta::GKV , std::__1::allocator > >::validate_override(llama_model_kv_override_type, llama_model_kv_override const*)	call site: 00419	__cxa_allocate_exception
8	628	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: 00628	ggml_nbytes

Runtime coverage analysis

Covered functions

239

Functions that are reachable but not covered

466

Reachable functions

783

Percentage of reachable functions covered

40.49%

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	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	6
/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	133
/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_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	1788	0	8009	7835
common_init_from_params(common_params&,bool)	/src/llama.cpp/common/common.cpp	3	['N/A', 'N/A', 'bool']	19	0	611	156	135	1928	0	14148	4175
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

2744 / 6479

Cyclomatic complexity statically reachable by fuzzers

28243 / 56776

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_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&)', '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&)', '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_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_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', '_ZN8GGUFMeta3GKVINSt3__112basic_stringIcNS1_11char_traitsIcEENS1_9allocatorIcEEEEE12try_overrideIS7_EENS1_9enable_ifIXsr3std7is_sameIT_S7_EE5valueEbE4typeERS7_PK23llama_model_kv_override']

/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_base::llama_model_base(llama_model_params 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(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()', '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*)', 'ggml_backend_dev_type', 'ggml_backend_dev_get', 'GGUFMeta::GKV_Base_Type::getter(gguf_context const*, 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*)']

/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_load_model', 'fuzz_inference', 'fuzz_structured']
llama_prepare_model_devices(llama_model_paramsconst&,llama_model*)	129	28	21.70%	['fuzz_load_model', 'fuzz_inference', 'fuzz_structured']
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
	[]	[]
/usr/local/bin/../include/c++/v1/initializer_list	[]	[]
/src/llama.cpp/src/models/arctic.cpp	[]	[]
/src/llama.cpp/src/models/gemma4-assistant.cpp	[]	[]
/src/llama.cpp/src/llama-context.cpp	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-impl.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/mistral3.cpp	[]	[]
/src/llama.cpp/src/models/apertus.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/refact.cpp	[]	[]
/src/llama.cpp/src/models/gemma.cpp	[]	[]
/src/llama.cpp/src/models/lfm2moe.cpp	[]	[]
/src/llama.cpp/src/models/kimi-linear.cpp	[]	[]
/src/llama.cpp/vendor/nlohmann/json_fwd.hpp	[]	[]
/src/llama.cpp/src/llama-model-saver.cpp	[]	[]
/usr/local/bin/../include/c++/v1/istream	[]	[]
/usr/local/bin/../include/c++/v1/__exception/exception_ptr.h	[]	[]
/src/llama.cpp/src/models/deepseek.cpp	[]	[]
/src/llama.cpp/src/models/rnd1.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-quants.c	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/./llama-batch.h	[]	[]
/src/llama.cpp/src/models/phi3.cpp	[]	[]
/usr/local/bin/../include/c++/v1/string	[]	[]
/src/llama.cpp/src/models/hunyuan-vl.cpp	[]	[]
/src/llama.cpp/src/models/gemma3n.cpp	[]	[]
/src/llama.cpp/src/models/glm4.cpp	[]	[]
/src/llama.cpp/src/llama-vocab.cpp	['fuzz_grammar', 'fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_grammar', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/phimoe.cpp	[]	[]
/src/llama.cpp/src/models/dflash.cpp	[]	[]
/src/llama.cpp/src/models/starcoder.cpp	[]	[]
/src/llama.cpp/src/models/exaone.cpp	[]	[]
/src/llama.cpp/src/models/step35.cpp	[]	[]
/src/llama.cpp/src/models/plamo3.cpp	[]	[]
/src/llama.cpp/src/models/dbrx.cpp	[]	[]
/src/llama.cpp/src/llama-graph.cpp	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/common/unicode.h	[]	[]
/src/llama.cpp/src/models/nomic-bert.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cells.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/llama-impl.h	[]	[]
/src/llama.cpp/src/llama-memory-hybrid.h	[]	[]
/src/llama.cpp/fuzzers/fuzz_grammar.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/modern-bert.cpp	[]	[]
/src/llama.cpp/common/fit.cpp	[]	[]
/src/llama.cpp/src/llama-io.cpp	[]	[]
/src/llama.cpp/src/llama-grammar.h	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/exaone-moe.cpp	[]	[]
/src/llama.cpp/src/models/jina-bert-v2.cpp	[]	[]
/src/llama.cpp/src/llama-graph.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/grok.cpp	[]	[]
/src/llama.cpp/src/models/cohere2moe.cpp	[]	[]
/src/llama.cpp/src/llama-batch.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/cohere2.cpp	[]	[]
/src/llama.cpp/src/models/grovemoe.cpp	[]	[]
/src/llama.cpp/src/models/mistral4.cpp	[]	[]
/src/llama.cpp/src/models/talkie.cpp	[]	[]
/src/llama.cpp/common/common.cpp	['fuzz_inference', 'fuzz_json_to_grammar']	['fuzz_inference', 'fuzz_json_to_grammar']
/src/llama.cpp/vendor/nlohmann/json.hpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/falcon-h1.cpp	[]	[]
/src/llama.cpp/src/models/llada-moe.cpp	[]	[]
/src/llama.cpp/src/models/bert.cpp	[]	[]
/src/llama.cpp/src/models/phi2.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-dsv4.cpp	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/ggml/src/ggml-backend-dl.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	[]
/src/llama.cpp/fuzzers/fuzz_apply_template.cpp	['fuzz_apply_template']	['fuzz_apply_template']
/src/llama.cpp/fuzzers/fuzz_inference.cpp	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/llama-impl.cpp	['fuzz_grammar', 'fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_grammar', 'fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/unicode-data.cpp	[]	[]
/src/llama.cpp/src/llama-vocab.h	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	[]
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp	[]	[]
/src/llama.cpp/common/reasoning-budget.cpp	[]	[]
/src/llama.cpp/src/./llama-impl.h	[]	[]
/src/llama.cpp/src/models/mamba-base.cpp	[]	[]
/src/llama.cpp/src/models/mamba2.cpp	[]	[]
/src/llama.cpp/src/llama-ext.h	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp	[]	[]
/usr/local/bin/../include/c++/v1/stdexcept	['fuzz_grammar', 'fuzz_json_to_grammar']	[]
/usr/local/bin/../include/c++/v1/__exception/exception.h	['fuzz_json_to_grammar']	[]
/src/llama.cpp/src/models/arcee.cpp	[]	[]
/src/llama.cpp/src/models/nomic-bert-moe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/vec.cpp	[]	[]
/src/llama.cpp/src/llama-mmap.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/paddleocr.cpp	[]	[]
/src/llama.cpp/src/models/gptneox.cpp	[]	[]
/src/llama.cpp/src/models/minicpm.cpp	[]	[]
/src/llama.cpp/src/models/ernie4-5-moe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/simd-gemm.h	[]	[]
/src/llama.cpp/src/models/wavtokenizer-dec.cpp	[]	[]
/src/llama.cpp/src/llama-io.h	[]	[]
/src/llama.cpp/src/llama-memory.cpp	[]	[]
/src/llama.cpp/src/models/qwen2vl.cpp	[]	[]
/src/llama.cpp/common/sampling.cpp	[]	[]
/src/llama.cpp/src/llama-memory.h	['fuzz_inference']	[]
/src/llama.cpp/src/llama.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_apply_template', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_apply_template', 'fuzz_load_model']
/src/llama.cpp/src/models/qwen2.cpp	[]	[]
/src/llama.cpp/src/models/smallthinker.cpp	[]	[]
/src/llama.cpp/src/llama-memory-recurrent.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/llama-cparams.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/baichuan.cpp	[]	[]
/src/llama.cpp/src/models/bailingmoe.cpp	[]	[]
/src/llama.cpp/src/models/gemma4.cpp	[]	[]
/src/llama.cpp/src/models/qwen3vlmoe.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/repack.cpp	[]	[]
/src/llama.cpp/src/models/plamo2.cpp	[]	[]
/src/llama.cpp/src/models/qwen.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-dsa.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/./llama-graph.h	[]	[]
/src/llama.cpp/src/models/dream.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-backend-dl.h	[]	[]
/src/llama.cpp/fuzzers/fuzz_structured.cpp	['fuzz_structured']	['fuzz_structured']
/src/llama.cpp/common/sampling.h	[]	[]
/src/llama.cpp/src/llama-hparams.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	[]
/src/llama.cpp/src/llama-batch.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/unicode.h	['fuzz_grammar']	[]
/src/llama.cpp/src/models/ernie4-5.cpp	[]	[]
/src/llama.cpp/src/llama-model-loader.h	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/t5encoder.cpp	[]	[]
/src/llama.cpp/src/models/olmo2.cpp	[]	[]
/src/llama.cpp/src/models/seed-oss.cpp	[]	[]
/src/llama.cpp/src/models/openelm.cpp	[]	[]
/src/llama.cpp/src/models/mamba.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/common/../vendor/nlohmann/json_fwd.hpp	[]	[]
/src/llama.cpp/src/models/hunyuan-moe.cpp	[]	[]
/src/llama.cpp/src/models/mellum.cpp	[]	[]
/src/llama.cpp/src/models/plamo.cpp	[]	[]
/src/llama.cpp/src/llama-context.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/qwen3moe.cpp	[]	[]
/src/llama.cpp/common/common.h	['fuzz_inference']	['fuzz_inference']
/src/llama.cpp/src/models/dots1.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-threading.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/neo-bert.cpp	[]	[]
/src/llama.cpp/src/models/mimo2.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6qwen2.cpp	[]	[]
/src/llama.cpp/ggml/src/./ggml-impl.h	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_inference']
/src/llama.cpp/src/models/olmo.cpp	[]	[]
/src/llama.cpp/src/models/glm4-moe.cpp	[]	[]
/src/llama.cpp/src/models/granite-moe.cpp	[]	[]
/src/llama.cpp/src/models/hy-v3.cpp	[]	[]
/src/llama.cpp/src/models/olmoe.cpp	[]	[]
/src/llama.cpp/src/models/nemotron.cpp	[]	[]
/src/llama.cpp/src/models/plm.cpp	[]	[]
/src/llama.cpp/src/models/deepseek2.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-opt.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/granite-hybrid.cpp	[]	[]
/src/llama.cpp/src/models/qwen3.cpp	[]	[]
/src/llama.cpp/src/models/eurobert.cpp	[]	[]
/src/llama.cpp/src/../include/llama-cpp.h	[]	[]
/src/llama.cpp/src/models/cogvlm.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/build/common/build-info.cpp	[]	[]
/src/llama.cpp/src/llama-model.h	[]	[]
/src/llama.cpp/src/models/rwkv7.cpp	[]	[]
/src/llama.cpp/src/llama-adapter.cpp	[]	[]
/src/llama.cpp/common/../src/llama-ext.h	[]	[]
/src/llama.cpp/common/../vendor/nlohmann/json.hpp	[]	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/mpt.cpp	[]	[]
/src/llama.cpp/src/llama-arch.h	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/ggml/src/ggml-backend-reg.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/ggml/src/ggml-backend-meta.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	[]
/src/llama.cpp/src/models/nemotron-h-moe.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-iswa.cpp	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-cpu/ops.cpp	[]	[]
/src/llama.cpp/src/models/gemma-embedding.cpp	[]	[]
/src/llama.cpp/src/models/starcoder2.cpp	[]	[]
/src/llama.cpp/src/models/minicpm3.cpp	[]	[]
/src/llama.cpp/src/models/openai-moe.cpp	[]	[]
/src/llama.cpp/src/models/gemma3.cpp	[]	[]
/src/llama.cpp/src/models/rwkv6-base.cpp	[]	[]
/src/llama.cpp/src/llama-memory-recurrent.h	[]	[]
/src/llama.cpp/src/models/stablelm.cpp	[]	[]
/src/llama.cpp/src/models/afmoe.cpp	[]	[]
/src/llama.cpp/src/models/models.h	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/jais.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h	[]	[]
/src/llama.cpp/src/llama-adapter.h	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-alloc.c	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-backend.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/bloom.cpp	[]	[]
/src/llama.cpp/src/models/deci.cpp	[]	[]
/src/llama.cpp/src/models/qwen3vl.cpp	[]	[]
/src/llama.cpp/src/models/deepseek32.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid.cpp	['fuzz_inference']	[]
/src/llama.cpp/ggml/src/ggml-cpu/traits.cpp	[]	[]
/src/llama.cpp/ggml/src/gguf.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/llama-model-loader.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/internlm2.cpp	[]	[]
/src/llama.cpp/common/log.cpp	[]	[]
/src/llama.cpp/src/models/bailingmoe2.cpp	[]	[]
/src/llama.cpp/src/models/exaone4.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml.c	['fuzz_grammar', 'fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/llama-grammar.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/qwen35.cpp	[]	[]
/src/llama.cpp/src/llama-sampler.h	[]	[]
/src/llama.cpp/src/models/bitnet.cpp	[]	[]
/src/llama.cpp/src/models/nemotron-h.cpp	[]	[]
/src/llama.cpp/src/models/qwen35moe.cpp	[]	[]
/src/llama.cpp/src/models/delta-net-base.cpp	[]	[]
/src/llama.cpp/src/models/falcon.cpp	[]	[]
/src/llama.cpp/src/models/orion.cpp	[]	[]
/src/llama.cpp/src/llama-model.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/llama4.cpp	[]	[]
/src/llama.cpp/src/models/pangu-embed.cpp	[]	[]
/src/llama.cpp/src/models/smollm3.cpp	[]	[]
/src/llama.cpp/src/models/jina-bert-v3.cpp	[]	[]
/src/llama.cpp/src/llama-memory-hybrid-iswa.h	[]	[]
/src/llama.cpp/src/llama-sampler.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/glm-dsa.cpp	[]	[]
/src/llama.cpp/src/models/qwen2moe.cpp	[]	[]
/src/llama.cpp/src/llama-chat.cpp	['fuzz_apply_template']	['fuzz_apply_template']
/src/llama.cpp/src/models/codeshell.cpp	[]	[]
/src/llama.cpp/src/models/t5.cpp	[]	[]
/src/llama.cpp/src/models/granite.cpp	[]	[]
/src/llama.cpp/src/models/jamba.cpp	[]	[]
/src/llama.cpp/src/models/chatglm.cpp	[]	[]
/src/llama.cpp/src/models/minimax-m2.cpp	[]	[]
/src/llama.cpp/src/models/deepseek2ocr.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/jais2.cpp	[]	[]
/src/llama.cpp/src/models/hunyuan-dense.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp	[]	[]
/src/llama.cpp/common/unicode.cpp	[]	[]
/src/llama.cpp/common/json-schema-to-grammar.h	['fuzz_json_to_grammar']	[]
/src/llama.cpp/src/llama-kv-cache-iswa.h	[]	[]
/src/llama.cpp/src/models/lfm2.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c	[]	[]
/src/llama.cpp/src/models/llama-embed.cpp	[]	[]
/src/llama.cpp/common/json-schema-to-grammar.cpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/src/models/llada.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/traits.h	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/quants.c	[]	[]
/src/llama.cpp/ggml/src/../include/ggml-cpp.h	[]	[]
/src/llama.cpp/src/models/maincoder.cpp	[]	[]
/src/llama.cpp/src/models/arwkv7.cpp	[]	[]
/src/llama.cpp/src/models/chameleon.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/vec.h	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/unicode.cpp	['fuzz_grammar']	['fuzz_grammar']
/src/llama.cpp/src/models/llama.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-dsv4.h	[]	[]
/src/llama.cpp/src/llama-memory-hybrid-iswa.cpp	['fuzz_inference']	[]
/src/llama.cpp/src/models/eagle3.cpp	[]	[]
/src/llama.cpp/src/models/qwen3next.cpp	[]	[]
/src/llama.cpp/src/llama-kv-cache-dsa.h	[]	[]
/src/llama.cpp/src/models/command-r.cpp	[]	[]
/src/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp	[]	[]
/src/llama.cpp/src/models/xverse.cpp	[]	[]
/src/llama.cpp/src/llama-arch.cpp	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']	['fuzz_structured', 'fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/ggml/src/ggml-cpu/common.h	[]	[]
/src/llama.cpp/src/./llama-arch.h	[]	['fuzz_inference', 'fuzz_load_model']
/src/llama.cpp/src/models/gpt2.cpp	[]	[]
/src/llama.cpp/src/models/gemma2.cpp	[]	[]
/src/llama.cpp/src/models/deepseek4.cpp	[]	[]
/src/llama.cpp/fuzzers/fuzz_json_to_grammar.cpp	['fuzz_json_to_grammar']	['fuzz_json_to_grammar']
/src/llama.cpp/fuzzers/fuzz_load_model.cpp	['fuzz_load_model']	['fuzz_load_model']
/src/llama.cpp/src/llama-hparams.h	['fuzz_inference']	[]
/src/llama.cpp/src/models/rwkv7-base.cpp	[]	[]

Directories in report

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