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

↓ 5 callersFunctionhvx_vec_load_mxfp4x4x8_full

ggml/src/ggml-hexagon/htp/matmul-ops.c:226

↓ 5 callersFunctionhvx_vec_load_mxfp4x4x8_partial

ggml/src/ggml-hexagon/htp/matmul-ops.c:259

↓ 5 callersFunctionhvx_vec_load_q4x4x8_full

ggml/src/ggml-hexagon/htp/matmul-ops.c:158

↓ 5 callersFunctionhvx_vec_load_q4x4x8_partial

ggml/src/ggml-hexagon/htp/matmul-ops.c:192

↓ 5 callersFunctionhvx_vec_reduce_max_f32

ggml/src/ggml-hexagon/htp/hvx-reduce.h:165

↓ 5 callersMethodin_example

common/arg.cpp:110

↓ 5 callersMethodinit

src/llama-mmap.cpp:760

↓ 5 callersFunctioniq2xs_free_impl

ggml/src/ggml-quants.c:3133

↓ 5 callersMethodisModelLoaded

* * * Status Queries * *

tools/server/webui/src/lib/stores/models.svelte.ts:220

↓ 5 callersMethodis_parent

tools/server/server-task.h:253

↓ 5 callersFunctionis_space_codepoint

common/console.cpp:577

↓ 5 callersFunctionlasx_set_w

ggml/src/ggml-cpu/arch/loongarch/quants.c:215

↓ 5 callersMethodlaunch

ggml/src/ggml-sycl/dpct/helper.hpp:3190

↓ 5 callersFunctionllama_get_embeddings_seq

src/llama-context.cpp:3155

↓ 5 callersFunctionllama_grammar_advance_stack

transforms a grammar pushdown stack into N possible stacks, all ending at a character range (terminal element)

src/llama-grammar.cpp:853

↓ 5 callersFunctionllama_memory_status_is_fail

src/llama-memory.cpp:44

↓ 5 callersFunctionllama_model_meta_val_str

src/llama-model.cpp:9553

↓ 5 callersFunctionllama_model_n_embd_out

src/llama-model.cpp:9343

↓ 5 callersFunctionllama_sample_dist

src/llama-sampler.cpp:217

↓ 5 callersFunctionllama_sampler_init_temp_ext

src/llama-sampler.cpp:2081

↓ 5 callersFunctionllama_split_path

src/llama.cpp:482

↓ 5 callersFunctionllama_state_seq_get_data_ext

src/llama-context.cpp:3437

↓ 5 callersFunctionllama_state_seq_get_size_ext

src/llama-context.cpp:3433

↓ 5 callersFunctionllama_vocab_eot

src/llama-vocab.cpp:3906

↓ 5 callersFunctionlsx_hadd_s

ggml/src/ggml-cpu/arch/loongarch/quants.c:92

↓ 5 callersFunctionmake_assistant_one_tool

tools/parser/template-analysis.cpp:221

↓ 5 callersFunctionmap_pydantic_type_to_gbnf

(pydantic_type: type[Any])

examples/pydantic_models_to_grammar.py:55

↓ 5 callersMethodmark_input_based_on

mark this string as input if other has ALL parts as input

common/jinja/string.cpp:98

↓ 5 callersFunctionmessage_with_reasoning_content_and_multiple_tool_calls

tests/test-chat.cpp:845

↓ 5 callersFunctionmtmd_input_chunk_get_n_pos

tools/mtmd/mtmd.cpp:1234

↓ 5 callersFunctionmtmd_input_chunk_get_type

tools/mtmd/mtmd.cpp:1202

↓ 5 callersFunctionmtmd_input_chunks_get

tools/mtmd/mtmd.cpp:1187

↓ 5 callersFunctionmtmd_input_chunks_size

tools/mtmd/mtmd.cpp:1183

↓ 5 callersFunctionmxfp4_extract_splat

ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:339

↓ 5 callersMethodn_bytes

src/llama-context.cpp:2388

↓ 5 callersMethodop

ggml/src/ggml-metal/ggml-metal-common.cpp:192

↓ 5 callersMethodop

ggml/src/ggml-hexagon/ggml-hexagon.cpp:2833

↓ 5 callersFunctionpackNibbles

ggml/src/ggml-cpu/amx/mmq.cpp:580

↓ 5 callersFunctionparallel_function_calls

Run multiple functions in parallel and return results in the same order as calls. Equivalent to Promise.all in JS. Example usage: resul

tools/server/tests/utils.py:602

↓ 5 callersFunctionparse_args

convert_hf_to_gguf.py:13961

↓ 5 callersFunctionparse_cpu_mask

common/common.cpp:327

↓ 5 callersFunctionparse_from_tokens

common/jinja/parser.cpp:598

↓ 5 callersMethodpos_in

check if a cell is not empty and its position is within [p0, p1)

src/llama-kv-cells.h:386

↓ 5 callersFunctionprev_utf8_char_pos

Helper function to remove the last UTF-8 character from a string

common/console.cpp:432

↓ 5 callersFunctionprint_fail

scripts/server-test-parallel-tc.py:85

↓ 5 callersFunctionprint_grammar_char

src/llama-grammar.cpp:231

↓ 5 callersFunctionprint_if_exists

(label, obj, attr, default="N/A")

examples/model-conversion/scripts/causal/run-org-model.py:45

↓ 5 callersMethodprint_test_result

tests/test-backend-ops.cpp:1034

↓ 5 callersMethodpush_front

common/jinja/value.cpp:61

↓ 5 callersFunctionq8x4x2_row_size

ggml/src/ggml-hexagon/htp/matmul-ops.c:151

↓ 5 callersMethodqueues_wait_and_throw

ggml/src/ggml-sycl/dpct/helper.hpp:725

↓ 5 callersFunctionread_file

common/arg.cpp:65

↓ 5 callersMethodread_str

tests/gguf-model-data.cpp:42

↓ 5 callersMethodrefreshActiveMessages

* Refreshes active messages based on currNode after branch navigation.

tools/server/webui/src/lib/stores/conversations.svelte.ts:397

↓ 5 callersFunctionreplace_last

common/console.cpp:356

↓ 5 callersMethodreset

common/reasoning-budget.cpp:36

↓ 5 callersFunctionround_down

ggml/src/ggml-cpu/kleidiai/kleidiai.cpp:420

↓ 5 callersMethodsend_data

ggml/src/ggml-rpc/transport.cpp:462

↓ 5 callersMethodseq_add

src/llama-kv-cache.cpp:514

↓ 5 callersMethodseq_pos_min

src/llama-kv-cache.cpp:593

↓ 5 callersFunctionserver_chat_convert_responses_to_chatcmpl

tools/server/server-chat.cpp:6

↓ 5 callersFunctionsimple_tokenize

tests/peg-parser/simple-tokenize.cpp:3

↓ 5 callersMethodskipFully

* Robust skip that works the same on JDK 11 and Android’s desugared runtime. * * @param n Number of bytes to advance in the stream. *

examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:545

↓ 5 callersMethodsplit_equal

src/llama-batch.cpp:508

↓ 5 callersFunctionstop

common/console.cpp:1128

↓ 5 callersMethodstreamChatCompletion

( allMessages: DatabaseMessage[], assistantMessage: DatabaseMessage, onComplete?: (content: string) => P

tools/server/webui/src/lib/stores/chat.svelte.ts:540

↓ 5 callersMethodterminate

tools/server/server-queue.cpp:119

↓ 5 callersFunctiontest_dry

tests/test-sampling.cpp:161

↓ 5 callersFunctiontest_reasoning_budget

Reasoning budget sampler test helper These tests use nullptr vocab which safely falls back to treating all tokens as complete (The UTF-8 boundary dete

tests/test-reasoning-budget.cpp:20

↓ 5 callersMethodtoDisplayName

* * * Utilities * *

tools/server/webui/src/lib/stores/models.svelte.ts:679

↓ 5 callersMethodto_string

common/arg.cpp:177

↓ 5 callersMethodtoken_bytes_to_string

convert_hf_to_gguf.py:3779

↓ 5 callersMethodtokenize

(self, text: str, add_special: bool = False, parse_special: bool = False)

tests/test-tokenizer-random.py:99

↓ 5 callersFunctiontokenize_input_subprompt

* break the input "prompt" object into multiple prompt if needed, then tokenize them * use tokenize_input_prompts() if the input could be an array.

tools/server/server-common.cpp:759

↓ 5 callersFunctiontransfer_output_chunk_threaded

ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:791

↓ 5 callersFunctiontranspose_16x16_32bit

ggml/src/ggml-cpu/amx/mmq.cpp:321

↓ 5 callersFunctiontrim_trailing_space

common/chat-peg-parser.cpp:11

↓ 5 callersFunctiontrim_trailing_whitespace

common/chat-auto-parser-helpers.cpp:42

↓ 5 callersMethodupdateConfig

* Update a specific configuration setting * @param key - The configuration key to update * @param value - The new value for the configuration key

tools/server/webui/src/lib/stores/settings.svelte.ts:166

↓ 5 callersMethodupdateConversation

* Updates a conversation. * * @param id - Conversation ID * @param updates - Partial updates to apply * @returns Promise that resolves when th

tools/server/webui/src/lib/services/database.service.ts:320

↓ 5 callersFunctionvalidate_float

ggml/src/ggml-quants.c:5162

↓ 5 callersMethodverify_status

tests/test-json-schema-to-grammar.cpp:57

↓ 5 callersMethodvisit

examples/json_schema_to_grammar.py:299

↓ 5 callersFunctionwebgpu_tensor_offset

Always returns the base offset of a tensor, regardless of views.

ggml/src/ggml-webgpu/ggml-webgpu.cpp:112

↓ 5 callersMethodwrite

tools/gguf-split/gguf-split.cpp:310

↓ 5 callersMethodwrite_padding

(self, fp: IO[bytes], n: int, align: int | None = None)

gguf-py/gguf/gguf_writer.py:401

↓ 4 callersMethod#proxyIconSrc

* Route an icon src through the CORS proxy if it's an HTTPS URL. * Data URIs are returned as-is.

tools/server/webui/src/lib/stores/mcp.svelte.ts:471

↓ 4 callersFunctionXXH3_reset_internal

examples/gguf-hash/deps/xxhash/xxhash.h:6170

↓ 4 callersFunctionXXH_mult64to128

! * @brief Calculates a 64->128-bit long multiply. * * Uses `__uint128_t` and `_umul128` if available, otherwise uses a scalar * version. * * @p

examples/gguf-hash/deps/xxhash/xxhash.h:4355

↓ 4 callersFunctionXXH_read32

* Force direct memory access. Only works on CPU which support unaligned memory * access in hardware. */

examples/gguf-hash/deps/xxhash/xxhash.h:2592

↓ 4 callersFunctionXXH_read64

Force direct memory access. Only works on CPU which support unaligned memory access in hardware */

examples/gguf-hash/deps/xxhash/xxhash.h:3268

↓ 4 callersFunctionXXH_writeLE64

examples/gguf-hash/deps/xxhash/xxhash.h:4837

↓ 4 callersMethod_doStopObserving

tools/server/webui/src/lib/hooks/use-auto-scroll.svelte.ts:238

↓ 4 callersMethod_push_field

(self, field: ReaderField, skip_sum: bool = False)

gguf-py/gguf/gguf_reader.py:206

↓ 4 callersMethod_reverse_hf_permute

(self, weights: Tensor, n_head: int, n_kv_head: int | None = None)

convert_hf_to_gguf.py:2599

↓ 4 callersMethod_strip_model_prefix

convert_hf_to_gguf.py:9291

↓ 4 callersFunction_util_sparse_array_node_level

ggml/src/ggml-virtgpu/virtgpu-utils.cpp:69

↓ 4 callersFunctionaclnn_arange

* @brief Creates a tensor with values starting from `start`, incremented by * `step`, and ending before `stop`. * * This function performs the oper

ggml/src/ggml-cann/aclnn_ops.cpp:341

↓ 4 callersFunctionaclnn_repeat

* @brief Repeats elements of a tensor along each dimension according to the * specified repeat array. * * @param ctx The context for the CANN backe

ggml/src/ggml-cann/aclnn_ops.cpp:164

↓ 4 callersMethodadd_architecture

gguf-py/gguf/gguf_writer.py:499

← previous next →1,501–1,600 of 13,473, ranked by callers