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

↓ 8 callersFunctionggml_node_get_use_count

ggml/src/ggml-impl.h:629

↓ 8 callersFunctionggml_op_is_empty

ggml/src/ggml-impl.h:90

↓ 8 callersFunctionggml_opt_result_reset

ggml/src/ggml-opt.cpp:647

↓ 8 callersFunctionggml_rope_impl

ggml/src/ggml.c:4125

↓ 8 callersFunctionggml_status_to_string

ggml/src/ggml.c:432

↓ 8 callersFunctionggml_swiglu_split

ggml/src/ggml.c:3027

↓ 8 callersFunctionggml_ue4m3_to_fp32

UE4M3: unsigned, 4 exp bits (bias=7), 3 mantissa bits Returns value * 0.5 to match kvalues_mxfp4 convention (kvalues = 2 * E2M1_float)

ggml/src/ggml-impl.h:502

↓ 8 callersFunctionggml_vec_dot_f32

ggml/src/ggml-cpu/vec.cpp:11

↓ 8 callersFunctionggml_vec_set_f32

ggml/src/ggml-cpu/vec.h:89

↓ 8 callersFunctionggml_vk_cpy_to_contiguous

ggml/src/ggml-vulkan/ggml-vulkan.cpp:7412

↓ 8 callersFunctionggml_vqtbl1q_u8

NOTE: not tested

ggml/src/ggml-cpu/ggml-cpu-impl.h:266

↓ 8 callersFunctiongguf_get_key

ggml/src/gguf.cpp:904

↓ 8 callersFunctiongguf_get_meta_size

ggml/src/gguf.cpp:1545

↓ 8 callersFunctiongguf_type_name

ggml/src/gguf.cpp:867

↓ 8 callersFunctionhex_l2fetch

ggml/src/ggml-hexagon/htp/hex-utils.h:77

↓ 8 callersFunctionhvx_vec_exp_f32

ggml/src/ggml-hexagon/htp/hvx-exp.h:23

↓ 8 callersMethodinit

src/llama-sampler.cpp:543

↓ 8 callersMethodinsert

common/json-schema-to-grammar.cpp:573

↓ 8 callersMethodis_running

tools/server/server-models.h:73

↓ 8 callersMethodis_static

ggml/src/ggml-openvino/openvino/node_context.h:95

↓ 8 callersFunctionllama_chat_apply_template

src/llama.cpp:447

↓ 8 callersFunctionllama_get_logits

src/llama-context.cpp:3123

↓ 8 callersFunctionllama_grammar_init_impl

src/llama-grammar.cpp:1126

↓ 8 callersFunctionllama_memory_seq_pos_max

src/llama-context.cpp:3335

↓ 8 callersFunctionllama_model_chat_template

src/llama-model.cpp:9618

↓ 8 callersFunctionllama_sampler_init_greedy

src/llama-sampler.cpp:1011

↓ 8 callersFunctionllama_sampler_init_top_p

src/llama-sampler.cpp:1513

↓ 8 callersFunctionllama_time_us

src/llama.cpp:110

↓ 8 callersFunctionlsx_packs_w

ggml/src/ggml-cpu/arch/loongarch/quants.c:28

↓ 8 callersFunctionlsx_shuffle_b

ggml/src/ggml-cpu/arch/loongarch/quants.c:68

↓ 8 callersMethodn_gqa

src/llama-hparams.cpp:54

↓ 8 callersFunctionparse_bool

* @brief Verify whether the environment variable is a valid value. */

ggml/src/ggml-cann/ggml-cann.cpp:116

↓ 8 callersMethodpos_get

note: call only if the cell is not empty

src/llama-kv-cells.h:363

↓ 8 callersMethodpost_task

tools/server/server-queue.cpp:343

↓ 8 callersFunctionquantize_row_q8_1_ref

reference implementation for deterministic creation of model files

ggml/src/ggml-quants.c:260

↓ 8 callersFunctionrandom_string

tools/server/server-common.cpp:64

↓ 8 callersMethodread_raw

src/llama-mmap.cpp:419

↓ 8 callersFunctionreplace_all

src/llama-impl.cpp:69

↓ 8 callersMethodreset

src/llama-kv-cells.h:34

↓ 8 callersFunctionserialize_tensor

ggml/src/ggml-rpc/ggml-rpc.cpp:424

↓ 8 callersMethodset_input_k_idxs

src/llama-kv-cache.cpp:1354

↓ 8 callersMethodset_input_kq_mask

src/llama-kv-cache.cpp:1608

↓ 8 callersFunctionstripLegacyContextMarkers

(content: string)

tools/server/webui/tests/unit/agentic-strip.test.ts:11

↓ 8 callersFunctionsummarize

Print a tensor in llama.cpp debug style. Supports: - 2D tensors (seq, hidden) - 3D tensors (batch, seq, hidden) - 4D tensors (ba

examples/model-conversion/scripts/utils/common.py:30

↓ 8 callersMethodtakeUnless

examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:479

↓ 8 callersMethodtext_to_token

src/llama-vocab.cpp:3625

↓ 8 callersFunctiontokenizer

tools/server/bench/script.js:33

↓ 8 callersMethodtool

Low-level tag methods

common/chat-peg-parser.h:79

↓ 8 callersMethodtool_args

common/chat-peg-parser.h:84

↓ 8 callersMethodtool_close

common/chat-peg-parser.h:81

↓ 8 callersFunctiontrim

============================================================== Utility: trim ==============================================================

ggml/src/ggml-webgpu/pre_wgsl.hpp:27

↓ 8 callersFunctiontrim_leading_whitespace

common/chat-auto-parser-helpers.cpp:33

↓ 8 callersFunctionunpack_mxfp4_quants

ggml/src/ggml-hexagon/ggml-hexagon.cpp:1038

↓ 8 callersFunctionunpack_q4_0_quants

ggml/src/ggml-hexagon/ggml-hexagon.cpp:351

↓ 8 callersFunctionunpack_q8_0_quants

ggml/src/ggml-hexagon/ggml-hexagon.cpp:693

↓ 8 callersFunctionuntil_common_prefix

Returns the prefix of `full` up until the first occurrence of the common prefix of `left` and `right`

common/chat-auto-parser-helpers.cpp:210

↓ 8 callersMethodupdateSession

(conversationId: string, update: Partial<AgenticSession>)

tools/server/webui/src/lib/stores/agentic.svelte.ts:144

↓ 8 callersMethodwrite_tensor

src/llama-context.cpp:2357

↓ 8 callersMethodwrite_tensors_to_file

(self, *, progress: bool = False)

gguf-py/gguf/gguf_writer.py:438

↓ 7 callersFunctionSHA1Update

examples/gguf-hash/deps/sha1/sha1.c:198

↓ 7 callersFunctionXXH64_avalanche

! @copydoc XXH32_avalanche */

examples/gguf-hash/deps/xxhash/xxhash.h:3435

↓ 7 callersFunctionXXH_mult32to64

! * @brief Calculates a 32-bit to 64-bit long multiply. * * Implemented as a macro. * * Wraps `__emulu` on MSVC x86 because it tends to call `__a

examples/gguf-hash/deps/xxhash/xxhash.h:4328

↓ 7 callersFunctionXXH_swap32

examples/gguf-hash/deps/xxhash/xxhash.h:2776

↓ 7 callersMethod_try_set_pooling_type

convert_hf_to_gguf.py:1862

↓ 7 callersFunctionaclnn_muls

* @brief Multiplies elements of a tensor by a scalar value, optionally * in-place. * * This function multiplies each element of the source tensor `

ggml/src/ggml-cann/aclnn_ops.cpp:265

↓ 7 callersMethodadd_chat_template

(self, value: str | Sequence[Mapping[str, str]])

gguf-py/gguf/gguf_writer.py:1105

↓ 7 callersMethodadd_expert_gating_func

(self, value: ExpertGatingFuncType)

gguf-py/gguf/gguf_writer.py:847

↓ 7 callersMethodadd_mask

src/models/deepseek4.cpp:59

↓ 7 callersMethodadd_ssm_conv_kernel

(self, value: int)

gguf-py/gguf/gguf_writer.py:1027

↓ 7 callersMethodadd_token_merges

(self, merges: Sequence[str] | Sequence[bytes] | Sequence[bytearray])

gguf-py/gguf/gguf_writer.py:1057

↓ 7 callersFunctionapir_decode_ggml_buffer

ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:100

↓ 7 callersFunctionapir_encode_bool_t

ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:340

↓ 7 callersFunctionapir_load_library_error

ggml/src/ggml-virtgpu/backend/shared/api_remoting.h:59

↓ 7 callersMethodapply

src/llama-adapter.cpp:94

↓ 7 callersFunctionatomic_fetch_add_explicit

ggml/src/ggml-cpu/ggml-cpu.c:136

↓ 7 callersFunctionatomic_store

ggml/src/ggml-cpu/ggml-cpu.c:119

↓ 7 callersFunctionatomic_store_explicit

ggml/src/ggml-cpu/ggml-cpu.c:122

↓ 7 callersFunctionbyte_level_permute

ggml/src/ggml-sycl/dpct/helper.hpp:2968

↓ 7 callersFunctioncheck_max_size

tests/test-alloc.cpp:195

↓ 7 callersFunctioncommon_log_set_verbosity_thold

common/log.cpp:30

↓ 7 callersFunctioncommon_ngram_cache_update

common/ngram-cache.cpp:12

↓ 7 callersFunctioncommon_perf_print

common/sampling.cpp:475

↓ 7 callersFunctioncosine_similarity

examples/model-conversion/scripts/utils/semantic_check.py:14

↓ 7 callersMethoddev_layer

src/llama-model.cpp:8495

↓ 7 callersFunctiondiv_up

ggml/src/ggml-cpu/amx/common.h:34

↓ 7 callersMethoddrain

tools/server/tests/unit/test_kv_keep_only_active.py:12

↓ 7 callersFunctiondsv4_apply_rope_tail

src/models/deepseek4.cpp:297

↓ 7 callersFunctiondsv4_cache_offset

src/llama-memory-hybrid-iswa.cpp:74

↓ 7 callersFunctiondsv4_make_state_layout

src/models/deepseek4.cpp:199

↓ 7 callersMethodempty

Check if a grammar is set

common/common.h:192

↓ 7 callersMethodencode

(self, text: str)

tests/test-tokenizer-random.py:121

↓ 7 callersFunctionextractJsonRpcMethods

(body: BodyInit | null | undefined)

tools/server/webui/src/lib/utils/request-helpers.ts:93

↓ 7 callersFunctionfilterByLeafNodeId

( messages: readonly DatabaseMessage[], leafNodeId: string, includeRoot: boolean = false )

tools/server/webui/src/lib/utils/branching.ts:40

↓ 7 callersFunctionformat_codepoint

Helper to format a code point as a readable string

tests/test-chat.cpp:130

↓ 7 callersFunctionfp32_from_bits

ggml/src/ggml-impl.h:366

↓ 7 callersMethodgetMessageByIdWithRole

( messageId: string, expectedRole?: MessageRole )

tools/server/webui/src/lib/stores/chat.svelte.ts:304

↓ 7 callersMethodgetServerDefaults

* Helper method to get server defaults with null safety * Centralizes the pattern of getting and extracting server defaults

tools/server/webui/src/lib/stores/settings.svelte.ts:76

↓ 7 callersMethodgetServers

tools/server/webui/src/lib/stores/mcp.svelte.ts:375

↓ 7 callersFunctionget_gguf_split_info

common/download.cpp:509

↓ 7 callersFunctionget_kv_str

tools/export-lora/export-lora.cpp:22

← previous next →1,001–1,100 of 13,473, ranked by callers