Functions — github.com/antirez/llama.cpp-deepseek-v4-flash

CodeHub MCPcopy Create free account

hub / github.com/antirez/llama.cpp-deepseek-v4-flash / functions

Functions13,473 in github.com/antirez/llama.cpp-deepseek-v4-flash

⨍ Functions 13,473◇ Types & classes 3,460↳ Endpoints 3

↓ 24 callersMethodget_shape

ggml/src/ggml-openvino/ggml-decoder.cpp:816

↓ 24 callersFunctionggml_backend_buffer_init

ggml/src/ggml-backend.cpp:87

↓ 24 callersFunctionggml_backend_dev_backend_reg

ggml/src/ggml-backend.cpp:594

↓ 24 callersFunctionggml_get_glu_op

ggml/src/ggml.c:1903

↓ 24 callersFunctiongguf_set_val_u32

ggml/src/gguf.cpp:1107

↓ 24 callersFunctionhvx_vec_splat_f16

ggml/src/ggml-hexagon/htp/hvx-base.h:46

↓ 24 callersMethodis_undefined

common/jinja/value.h:140

↓ 24 callersFunctionlasx_extracti128

ggml/src/ggml-cpu/arch/loongarch/quants.c:253

↓ 24 callersFunctionllama_model_load_from_file

src/llama.cpp:403

↓ 24 callersFunctionmul_add_epi8_sse

ggml/src/ggml-cpu/arch/x86/quants.c:173

↓ 24 callersMethodnegate

Negative lookahead: succeeds if child parser fails, consumes no input. S -> !A

common/peg-parser.h:403

↓ 24 callersMethodnumpy

convert_hf_to_gguf.py:13898

↓ 24 callersFunctionpreprocessLaTeX

(content: string)

tools/server/webui/src/lib/utils/latex-protection.ts:147

↓ 24 callersFunctionstring_starts_with

remove when moving to c++20

tools/mtmd/clip-impl.h:536

↓ 24 callersFunctiontest_sampler_queue

tests/test-sampling.cpp:195

↓ 23 callersMethod_add_rule

(self, name, rule)

examples/json_schema_to_grammar.py:325

↓ 23 callersMethodadd_input

src/llama-graph.cpp:931

↓ 23 callersFunctionassert_gbnf_equal

tests/peg-parser/test-gbnf-generation.cpp:12

↓ 23 callersMethodensure_count

common/jinja/value.h:655

↓ 23 callersMethodget_field

(self, key: str)

gguf-py/gguf/gguf_reader.py:190

↓ 23 callersFunctionggml_clamp

ggml/src/ggml.c:4384

↓ 23 callersFunctionggml_graph_n_nodes

ggml/src/ggml.c:7454

↓ 23 callersFunctionggml_time_ms

ggml/src/ggml.c:534

↓ 23 callersFunctionggml_webgpu_tensor_align_offset

ggml/src/ggml-webgpu/ggml-webgpu.cpp:409

↓ 23 callersMethodis_debug

common/peg-parser.h:181

↓ 23 callersFunctionllama_sampler_init

src/llama-sampler.cpp:351

↓ 23 callersFunctionllama_vocab_get_add_bos

src/llama-vocab.cpp:3927

↓ 23 callersMethodparse_anywhere_and_extract

common/chat-peg-parser.cpp:180

↓ 23 callersFunctionremote_call_finish

ggml/src/ggml-virtgpu/virtgpu.cpp:414

↓ 23 callersMethodrest

Matches everything S -> .

common/peg-parser.h:434

↓ 23 callersMethodsynchronize

src/llama-context.cpp:648

↓ 23 callersMethodtoken_to_piece

tests/test-backend-sampler.cpp:249

↓ 23 callersFunctionunicode_cpt_to_utf8

src/unicode.cpp:955

↓ 22 callersFunctionalign_to

ggml/src/ggml-opencl/ggml-opencl.cpp:128

↓ 22 callersMethodapply

tests/test-sampling.cpp:44

↓ 22 callersFunctionconfig

tools/server/webui/src/lib/stores/settings.svelte.ts:454

↓ 22 callersFunctionggml_backend_buffer_free

ggml/src/ggml-backend.cpp:107

↓ 22 callersFunctionggml_backend_buffer_get_base

ggml/src/ggml-backend.cpp:123

↓ 22 callersFunctionggml_backend_get_device

ggml/src/ggml-backend.cpp:470

↓ 22 callersFunctionggml_unary

ggml/src/ggml.c:5835

↓ 22 callersFunctionggml_webgpu_tensor_binding_size

ggml/src/ggml-webgpu/ggml-webgpu.cpp:414

↓ 22 callersFunctionhvx_vec_load_q8x4x8_full

ggml/src/ggml-hexagon/htp/matmul-ops.c:293

↓ 22 callersFunctionllama_vocab_is_eog

src/llama-vocab.cpp:3890

↓ 22 callersMethodreset

src/llama-graph.cpp:833

↓ 22 callersMethodresolve_refs

common/peg-parser.cpp:946

↓ 22 callersMethodtrigger_rule

Creates a trigger rule. When generating a lazy grammar from the parser, only trigger rules and descendents are emitted.

common/peg-parser.h:501

↓ 22 callersMethodupdateMessage

(messageId: string, newContent: string)

tools/server/webui/src/lib/stores/chat.svelte.ts:886

↓ 22 callersMethodupdateMessageAtIndex

* Updates a message at a specific index in active messages

tools/server/webui/src/lib/stores/conversations.svelte.ts:182

↓ 22 callersMethodwrite

convert_hf_to_gguf.py:948

↓ 21 callersFunctionbuild_chat_peg_parser

common/chat-peg-parser.h:156

↓ 21 callersFunctioncommon_chat_template_direct_apply

common/chat.cpp:808

↓ 21 callersFunctioncommon_log_main

common/log.cpp:370

↓ 21 callersFunctionfuzz_test_template

Helper to execute a fuzz test case - returns true if no crash occurred

tests/test-jinja.cpp:2113

↓ 21 callersMethodget_size

ggml/src/ggml-sycl/dpct/helper.hpp:1467

↓ 21 callersFunctionggml_backend_dev_by_type

ggml/src/ggml-backend-reg.cpp:336

↓ 21 callersFunctionggml_backend_dev_description

ggml/src/ggml-backend.cpp:573

↓ 21 callersFunctionggml_gelu

ggml/src/ggml.c:2748

↓ 21 callersFunctionggml_norm

ggml/src/ggml.c:3106

↓ 21 callersFunctionggml_repeat_4d

ggml/src/ggml.c:2550

↓ 21 callersFunctionggml_sub

ggml/src/ggml.c:2209

↓ 21 callersFunctionggml_vk_op_f32

ggml/src/ggml-vulkan/ggml-vulkan.cpp:9930

↓ 21 callersFunctiongguf_get_arr_n

ggml/src/gguf.cpp:932

↓ 21 callersFunctionhvx_vec_load_q8x4x8_partial

ggml/src/ggml-hexagon/htp/matmul-ops.c:309

↓ 21 callersFunctionllama_vocab_eos

src/llama-vocab.cpp:3902

↓ 21 callersFunctionmessage_with_tool_calls

tests/test-chat.cpp:835

↓ 21 callersMethodn_tokens

src/llama-vocab.cpp:3551

↓ 21 callersFunctionparse_space

src/llama-grammar.cpp:125

↓ 21 callersMethodread

src/llama-context.cpp:2382

↓ 21 callersMethodread_val

tests/gguf-model-data.cpp:33

↓ 21 callersMethodreset

ggml/src/ggml-sycl/dpct/helper.hpp:713

↓ 21 callersFunctionset_display

Keep track of current display and only emit ANSI code if it changes

common/console.cpp:173

↓ 21 callersFunctionvec_hsum_i32x4

ggml/src/ggml-cpu/ggml-cpu-impl.h:504

↓ 20 callersMethodadd_layer_norm_eps

(self, value: float)

gguf-py/gguf/gguf_writer.py:910

↓ 20 callersMethodadd_rope_scaling_type

(self, value: RopeScalingType)

gguf-py/gguf/gguf_writer.py:994

↓ 20 callersMethodget_rope_factors

src/llama-model.cpp:8577

↓ 20 callersFunctionget_value

ggml/src/ggml-sycl/dpct/helper.hpp:1687

↓ 20 callersFunctionggml_backend_dev_get

ggml/src/ggml-backend-reg.cpp:321

↓ 20 callersFunctionggml_cont_4d

ggml/src/ggml.c:3564

↓ 20 callersFunctionggml_get_type_traits_cpu

ggml/src/ggml-cpu/ggml-cpu.c:404

↓ 20 callersFunctionggml_hash_find

ggml/src/ggml-impl.h:259

↓ 20 callersFunctionggml_is_empty

ggml/src/ggml.c:1520

↓ 20 callersFunctionhex_align_up

ggml/src/ggml-hexagon/htp/hex-utils.h:51

↓ 20 callersFunctionllama_get_sampled_token_ith

src/llama-context.cpp:3165

↓ 20 callersFunctionllama_model_default_params

src/llama-model.cpp:9295

↓ 20 callersFunctionllama_sampler_apply

src/llama-sampler.cpp:378

↓ 20 callersFunctionllama_sampler_free

src/llama-sampler.cpp:416

↓ 20 callersFunctionmore_digits

(min_digits: int, max_digits: int)

examples/json_schema_to_grammar.py:41

↓ 20 callersMethodn_rot

src/llama-hparams.cpp:65

↓ 20 callersFunctionrename_outputs_with_suffix

ggml/src/ggml-openvino/openvino/utils.cpp:66

↓ 20 callersMethodu32

examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:199

↓ 19 callersFunctionXXH_readLE32

examples/gguf-hash/deps/xxhash/xxhash.h:2806

↓ 19 callersFunctionadd

ggml/src/ggml-cpu/llamafile/sgemm.cpp:88

↓ 19 callersFunctionadd_tensor

ggml/src/ggml-rpc/ggml-rpc.cpp:674

↓ 19 callersMethodalloc

* @brief Allocates memory from the pool. * @param size Size of the memory block to allocate. * @return Pointer to the allocated memory block

ggml/src/ggml-cann/common.h:179

↓ 19 callersMethodany

Matches any single character. S -> .

common/peg-parser.h:407

↓ 19 callersMethodcontiguous

convert_lora_to_gguf.py:131

↓ 19 callersMethoddigest

finalize and get the hash value note: after calling digest, the hasher state is modified, do not call update() again

common/jinja/utils.h:118

↓ 19 callersFunctionfastmodulo

ggml/src/ggml-hexagon/htp/hex-fastdiv.h:33

↓ 19 callersFunctionget_current_device_id

ggml/src/ggml-sycl/common.cpp:18

↓ 19 callersFunctionget_int_from_uint8

ggml/src/ggml-sycl/vecdotq.hpp:60

← previous next →401–500 of 13,473, ranked by callers