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

↓ 48 callersFunctioninit_tensor_uniform

tests/test-backend-ops.cpp:52

↓ 48 callersMethodjson

common/peg-parser.cpp:1359

↓ 48 callersMethodread_to

src/llama-context.cpp:2377

↓ 47 callersFunctionggml_vk_dispatch_pipeline

ggml/src/ggml-vulkan/ggml-vulkan.cpp:6603

↓ 47 callersMethodpost

tools/server/server-http.cpp:438

↓ 47 callersMethodwrite

tools/server/server-models.cpp:1095

↓ 46 callersMethodadd_float32

(self, key: str, val: float)

gguf-py/gguf/gguf_writer.py:301

↓ 46 callersMethodcontent

common/chat-peg-parser.h:72

↓ 46 callersMethoddelete

* Delete a specific key from cache.

tools/server/webui/src/lib/utils/cache-ttl.ts:98

↓ 46 callersFunctionggml_backend_dev_name

ggml/src/ggml-backend.cpp:568

↓ 46 callersFunctionggml_pipeline_request_descriptor_sets

ggml/src/ggml-vulkan/ggml-vulkan.cpp:2351

↓ 46 callersMethodparse_args

common/jinja/parser.cpp:468

↓ 46 callersMethodread

tools/server/server-models.cpp:1076

↓ 45 callersMethodconnect

ggml/src/ggml-rpc/transport.cpp:627

↓ 45 callersFunctionggml_add_or_set

ggml/src/ggml.c:6470

↓ 45 callersFunctionhsum_float_8

horizontally add 8 floats

ggml/src/ggml-cpu/arch/x86/quants.c:43

↓ 44 callersMethodadd_feed_forward_length

(self, length: int | Sequence[int])

gguf-py/gguf/gguf_writer.py:718

↓ 44 callersFunctionggml_vk_sync_buffers

ggml/src/ggml-vulkan/ggml-vulkan.cpp:2853

↓ 44 callersFunctiongguf_find_key

ggml/src/gguf.cpp:888

↓ 44 callersFunctionhelper_write

tests/test-gguf.cpp:157

↓ 44 callersFunctionload

ggml/src/ggml-cpu/llamafile/sgemm.cpp:305

↓ 43 callersMethodclose

gguf-py/gguf/gguf_writer.py:490

↓ 43 callersFunctionggml_new_tensor_3d

ggml/src/ggml.c:1834

↓ 43 callersFunctionggml_sycl_set_device

ggml/src/ggml-sycl/common.hpp:193

↓ 43 callersMethodpermute

(weights: Tensor, n_head: int, n_head_kv: int | None)

convert_hf_to_gguf.py:3400

↓ 43 callersMethodstr

src/llama-arch.cpp:839

↓ 43 callersMethodstring

common/jinja/string.h:26

↓ 42 callersMethodadd_context_length

(self, length: int)

gguf-py/gguf/gguf_writer.py:682

↓ 42 callersFunctionllama_sampler_chain_init

src/llama-sampler.cpp:792

↓ 42 callersFunctionllama_vocab_n_tokens

src/llama-vocab.cpp:3865

↓ 42 callersMethodlog

tests/testing.h:40

↓ 41 callersFunctionformat_error_response

tools/server/server-common.cpp:16

↓ 41 callersMethodget_model_id_components

(model_id: Optional[str] = None, total_params: int = 0)

gguf-py/gguf/metadata.py:240

↓ 41 callersFunctionggml_vk_subbuffer

ggml/src/ggml-vulkan/ggml-vulkan.cpp:2849

↓ 41 callersMethodpop

src/llama-vocab.cpp:260

↓ 41 callersMethodstr

tools/server/server-common.cpp:319

↓ 40 callersFunctionggml_view_tensor

ggml/src/ggml.c:1929

↓ 39 callersMethod_set_special_token

(self, typ: str, tid: Any)

gguf-py/gguf/vocab.py:137

↓ 39 callersMethodas_int

common/jinja/value.h:132

↓ 39 callersFunctionex_wrapper

wrapper function that handles exceptions and logs errors this is to make sure handler_t never throws exceptions; instead, it returns an error response

tools/server/server.cpp:40

↓ 39 callersFunctionllama_sampler_chain_default_params

src/llama.cpp:49

↓ 39 callersMethodn_head_kv

src/llama-hparams.cpp:38

↓ 38 callersMethodadd_head_count

(self, count: int | Sequence[int])

gguf-py/gguf/gguf_writer.py:754

↓ 38 callersMethodadd_rope_dimension_count

(self, count: int)

gguf-py/gguf/gguf_writer.py:982

↓ 38 callersMethodadd_token_list

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

gguf-py/gguf/gguf_writer.py:1054

↓ 38 callersFunctioncommon_batch_clear

common/common.cpp:1544

↓ 38 callersFunctionggml_barrier

ggml/src/ggml-cpu/ggml-cpu.c:562

↓ 38 callersFunctionllama_backend_init

src/llama.cpp:83

↓ 38 callersFunctionpermute_sub_group_by_xor

ggml/src/ggml-sycl/dpct/helper.hpp:1822

↓ 38 callersMethodwrite

ggml/src/gguf.cpp:1397

↓ 37 callersMethodadd_block_count

(self, length: int)

gguf-py/gguf/gguf_writer.py:709

↓ 37 callersMethodadd_tokenizer_model

(self, model: str)

gguf-py/gguf/gguf_writer.py:1048

↓ 37 callersFunctiondma_queue_push_ddr_to_vtcm

ggml/src/ggml-hexagon/htp/hex-dma.h:312

↓ 37 callersMethodget_key_or_arr

src/llama-model-loader.cpp:438

↓ 37 callersFunctionggml_cast

ggml/src/ggml.c:3504

↓ 37 callersMethodn_head

src/llama-hparams.cpp:30

↓ 37 callersMethodupdate

src/llama-kv-cache.cpp:741

↓ 37 callersMethodzero_or_more

Matches zero or more repetitions of a parser, always succeeds. S -> A

common/peg-parser.h:391

↓ 36 callersMethodadd_embedding_length

(self, length: int)

gguf-py/gguf/gguf_writer.py:685

↓ 36 callersMethodadd_file_type

(self, ftype: int)

gguf-py/gguf/gguf_writer.py:511

↓ 36 callersMethodadd_token_types

(self, types: Sequence[TokenType] | Sequence[int])

gguf-py/gguf/gguf_writer.py:1060

↓ 36 callersMethodbuild_grammar

GBNF generation implementation

common/peg-parser.cpp:1599

↓ 36 callersFunctionbuild_tagged_peg_parser

common/chat-peg-parser.cpp:196

↓ 36 callersMethodchoice

common/peg-parser.cpp:1189

↓ 36 callersMethodclear

common/sampling.cpp:89

↓ 36 callersFunctionggml_rope_multi

ggml/src/ggml.c:4193

↓ 36 callersFunctiongguf_get_n_kv

ggml/src/gguf.cpp:884

↓ 36 callersFunctionllama_batch_init

src/llama-batch.cpp:877

↓ 36 callersFunctionllama_free

src/llama-context.cpp:3048

↓ 36 callersFunctionllama_sampler_init_dist

src/llama-sampler.cpp:1230

↓ 36 callersMethodmarker

common/peg-parser.cpp:1443

↓ 36 callersFunctionselect_from_sub_group

ggml/src/ggml-sycl/dpct/helper.hpp:3237

↓ 35 callersMethodadd_to_gguf

(self, gw: GGUFWriter, quiet: bool = False)

gguf-py/gguf/vocab.py:78

↓ 35 callersFunctionalmost_equal

tests/test-opt.cpp:18

↓ 35 callersFunctioncommon_init

common/common.cpp:363

↓ 35 callersFunctionggml_webgpu_create_pipeline

ggml/src/ggml-webgpu/ggml-webgpu.cpp:339

↓ 35 callersFunctionggml_webgpu_make_bind_group_entry

ggml/src/ggml-webgpu/ggml-webgpu.cpp:448

↓ 35 callersFunctionggml_webgpu_tensor_buf

ggml/src/ggml-webgpu/ggml-webgpu.cpp:382

↓ 35 callersMethodmap_tensor_name

(self, name: str, try_suffixes: Sequence[str] = (".weight", ".bias"))

convert_hf_to_gguf.py:545

↓ 35 callersMethodref

Creates a lightweight reference to a named rule (resolved during build()). Use this for forward references in recursive grammars. expr_ref -> expr

common/peg-parser.h:418

↓ 35 callersMethodsize

src/llama-model.cpp:8227

↓ 34 callersMethodadd_array

(self, key: str, val: Sequence[Any])

gguf-py/gguf/gguf_writer.py:321

↓ 34 callersMethodadd_clip_projector_type

(self, value: str)

gguf-py/gguf/gguf_writer.py:1151

↓ 34 callersMethodchars

common/peg-parser.cpp:1221

↓ 34 callersMethoddecode

src/llama-context.cpp:1549

↓ 34 callersMethodempty

examples/speculative-simple/speculative-simple.cpp:25

↓ 34 callersMethodget_recr

src/llama-memory-hybrid.cpp:266

↓ 34 callersFunctionget_type_combination_id

ggml/src/ggml-sycl/dpct/helper.hpp:1131

↓ 34 callersFunctionggml_backend_buffer_is_host

ggml/src/ggml-backend.cpp:174

↓ 34 callersFunctionggml_backend_buft_name

ggml/src/ggml-backend.cpp:33

↓ 34 callersFunctionggml_backend_cpu_buffer_type

ggml/src/ggml-backend.cpp:2328

↓ 34 callersFunctionggml_backend_name

ggml/src/ggml-backend.cpp:222

↓ 34 callersFunctionggml_cann_create_scalar

ggml/src/ggml-cann/acl_tensor.cpp:100

↓ 34 callersFunctionhvx_vec_store_u

ggml/src/ggml-hexagon/htp/hvx-base.h:15

↓ 34 callersFunctionjoin

tools/llama-bench/llama-bench.cpp:83

↓ 34 callersFunctionllama_n_ctx

src/llama-context.cpp:3052

↓ 34 callersMethodpreprocess

ggml/src/ggml-webgpu/pre_wgsl.hpp:449

↓ 34 callersMethodstr

examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:196

↓ 33 callersMethodadd_head_count_kv

(self, count: int | Sequence[int])

gguf-py/gguf/gguf_writer.py:760

↓ 33 callersMethodallocate

ggml/src/ggml-opencl/ggml-opencl.cpp:281

← previous next →201–300 of 13,473, ranked by callers