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

↓ 6 callersFunctiongguf_get_tensor_type

ggml/src/gguf.cpp:1053

↓ 6 callersFunctiongguf_set_arr_str

ggml/src/gguf.cpp:1168

↓ 6 callersFunctiongguf_write_to_file

ggml/src/gguf.cpp:1528

↓ 6 callersFunctionhasClipboardAttachments

(clipboardText: string)

tools/server/webui/src/lib/utils/clipboard.ts:304

↓ 6 callersMethodhas_input

ggml/src/ggml-openvino/openvino/node_context.h:79

↓ 6 callersFunctionhex_round_up

ggml/src/ggml-hexagon/ggml-hexagon.cpp:78

↓ 6 callersFunctionhmx_mul_overflow

ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:103

↓ 6 callersFunctionhvx_cumsum_vadd

ggml/src/ggml-hexagon/htp/cumsum-ops.c:61

↓ 6 callersFunctionhvx_vec_exp_f32_guard

ggml/src/ggml-hexagon/htp/hvx-exp.h:141

↓ 6 callersFunctionhvx_vec_i16_from_hf_rnd_sat

ggml/src/ggml-hexagon/htp/hvx-base.h:187

↓ 6 callersFunctionhvx_vec_inverse_f16

Find reciprocal of fp16. (1) first, convert to fp32, multiplying by 1.0; this is done to handle denormals. Ignoring sign and zero, result should be at

ggml/src/ggml-hexagon/htp/hvx-inverse.h:44

↓ 6 callersMethodinit

ggml/src/ggml-vulkan/ggml-vulkan.cpp:903

↓ 6 callersFunctioniq2_find_best_neighbour

ggml/src/ggml-quants.c:3143

↓ 6 callersFunctionisRouterMode

tools/server/webui/src/lib/stores/server.svelte.ts:157

↓ 6 callersFunctionisTemplateComplete

(template: string, values: Record<string, string>)

tools/server/webui/src/lib/utils/uri-template.ts:194

↓ 6 callersMethodis_hashable

common/jinja/value.h:153

↓ 6 callersFunctionlasx_extractf128

ggml/src/ggml-cpu/arch/loongarch/quants.c:264

↓ 6 callersFunctionlasx_xvandi_b_bit

ggml/src/ggml-cpu/arch/loongarch/quants.c:324

↓ 6 callersFunctionllama_detokenize

src/llama-vocab.cpp:4093

↓ 6 callersFunctionllama_encode

src/llama-context.cpp:3473

↓ 6 callersFunctionllama_get_sampled_logits_ith

src/llama-context.cpp:3177

↓ 6 callersFunctionllama_grammar_free_impl

src/llama-grammar.cpp:1301

↓ 6 callersFunctionllama_memory_seq_keep

src/llama-context.cpp:3289

↓ 6 callersFunctionllama_model_has_encoder

src/llama-model.cpp:9641

↓ 6 callersFunctionllama_n_seq_max

src/llama-context.cpp:3068

↓ 6 callersFunctionllama_sampler_reset

src/llama-sampler.cpp:387

↓ 6 callersFunctionllama_state_seq_set_data_ext

src/llama-context.cpp:3443

↓ 6 callersFunctionllama_supports_gpu_offload

src/llama.cpp:73

↓ 6 callersFunctionllama_vocab_fim_sep

src/llama-vocab.cpp:3959

↓ 6 callersFunctionllama_vocab_sep

src/llama-vocab.cpp:3915

↓ 6 callersFunctionllm_arch_from_string

src/llama-arch.cpp:870

↓ 6 callersFunctionload_model

tools/mtmd/legacy-models/llava_surgery_v2.py:15

↓ 6 callersMethodload_page

Load the current page of tokenizer data.

gguf-py/gguf/scripts/gguf_editor_gui.py:169

↓ 6 callersMethodload_page

Load the current page of array values.

gguf-py/gguf/scripts/gguf_editor_gui.py:495

↓ 6 callersFunctionload_seed_oss_template

Helper to load Seed-OSS template

tests/test-chat-auto-parser.cpp:768

↓ 6 callersFunctionmakeToolMsg

(overrides: Partial<DatabaseMessage> = {})

tools/server/webui/tests/unit/agentic-sections.test.ts:21

↓ 6 callersFunctionmul_add_epi8

ggml/src/ggml-cpu/arch/loongarch/quants.c:1960

↓ 6 callersMethodn_embd_head_k_mla

src/llama-hparams.cpp:231

↓ 6 callersMethodn_embd_head_v_mla

src/llama-hparams.cpp:235

↓ 6 callersMethodn_tokens

0-based position of this image among image chunks in the prompt(used by pos == MTMD_POS_TYPE_HUNYUANVL)

tools/mtmd/mtmd.cpp:48

↓ 6 callersFunctionnext_utf8_char_pos

common/console.cpp:441

↓ 6 callersFunctionoaicompat_chat_params_parse

used by /chat/completions endpoint

tools/server/server-common.cpp:911

↓ 6 callersFunctionparse_key_spec

Helper: Parse dot notation key into prefix and field name

common/chat-peg-parser.cpp:566

↓ 6 callersFunctionprint_fail

scripts/server-test-structured.py:76

↓ 6 callersFunctionprint_usage

examples/simple/simple.cpp:8

↓ 6 callersFunctionprint_usage

examples/simple-chat/simple-chat.cpp:9

↓ 6 callersFunctionprocess_view_input

ggml/src/ggml-openvino/openvino/utils.cpp:234

↓ 6 callersMethodprompt_clear

tools/server/server-context.cpp:159

↓ 6 callersFunctionquantize_row_q8_K_ref

ggml/src/ggml-quants.c:2692

↓ 6 callersMethodread_u32

src/llama-mmap.cpp:426

↓ 6 callersFunctionredactValue

(value: string, showLastChars?: number)

tools/server/webui/src/lib/utils/redact.ts:8

↓ 6 callersMethodseq_pos_max

src/llama-batch.cpp:461

↓ 6 callersMethodset

src/llama-model-loader.cpp:251

↓ 6 callersMethodset_input_v_idxs

src/llama-kv-cache.cpp:1370

↓ 6 callersMethodset_input_v_rot

src/llama-kv-cache.cpp:1681

↓ 6 callersMethodset_option

common/preset.cpp:120

↓ 6 callersMethodshowErrorDialog

(state: ErrorDialogState | null)

tools/server/webui/src/lib/stores/chat.svelte.ts:179

↓ 6 callersMethodsize

src/llama-kv-cache.h:57

↓ 6 callersMethodsplit_reset

src/llama-batch.cpp:465

↓ 6 callersFunctionstring_ends_with

remove when moving to c++20

tools/mtmd/clip-impl.h:542

↓ 6 callersFunctionstring_remove_suffix

common/common.h:760

↓ 6 callersFunctiontest_penalties

tests/test-sampling.cpp:139

↓ 6 callersMethodtofile

(self, *args, **kwargs)

gguf-py/gguf/lazy.py:224

↓ 6 callersMethodtoken_bos

src/llama-vocab.cpp:3653

↓ 6 callersMethodtoken_eos

src/llama-vocab.cpp:3657

↓ 6 callersFunctiontokenize_mixed

tools/server/server-common.cpp:641

↓ 6 callersMethodtool_id

common/chat-peg-parser.h:82

↓ 6 callersFunctionuniform_range

(from_str: str, to_str: str)

examples/json_schema_to_grammar.py:53

↓ 6 callersMethodupdateHealthCheck

(serverId: string, state: HealthCheckState)

tools/server/webui/src/lib/stores/mcp.svelte.ts:346

↓ 6 callersMethoduse_mrope

src/llama-hparams.cpp:264

↓ 6 callersMethodvalid_format

(data_files: list[str])

scripts/compare-llama-bench.py:553

↓ 6 callersFunctionvirtgpu_ioctl

ggml/src/ggml-virtgpu/virtgpu.h:103

↓ 6 callersFunctionvirtgpu_shmem_create

ggml/src/ggml-virtgpu/virtgpu-shm.cpp:74

↓ 6 callersFunctionwrite_qdc_log

Push content as a log file to QDC_LOGS_PATH on the device for QDC log collection.

scripts/snapdragon/qdc/tests/utils.py:65

↓ 6 callersMethodwrite_u32

src/llama-mmap.cpp:429

↓ 5 callersFunctionXXH32_avalanche

! * @internal * @brief Mixes all bits to finalize the hash. * * The final mix ensures that all input bits have a chance to impact any bit in * th

examples/gguf-hash/deps/xxhash/xxhash.h:2948

↓ 5 callersMethod__init__

(self, tool: str = "llama-bench")

scripts/compare-llama-bench.py:223

↓ 5 callersMethod_builds_init

scripts/compare-llama-bench.py:238

↓ 5 callersFunction_get_model_status

(model_id: str)

tools/server/tests/unit/test_router.py:65

↓ 5 callersFunctionaclnn_add

ggml/src/ggml-cann/aclnn_ops.cpp:207

↓ 5 callersFunctionaclnn_permute

* @brief Permutes the dimensions of a tensor according to a specified order. * * This function permutes the dimensions of the source tensor `acl_src

ggml/src/ggml-cann/aclnn_ops.cpp:1123

↓ 5 callersFunctionadd_channel_bias

tools/mtmd/models/yasa2.cpp:6

↓ 5 callersFunctionadd_key_str

(raw_key: str, arch: str)

tools/mtmd/legacy-models/minicpmv-convert-image-encoder-to-gguf.py:422

↓ 5 callersMethodadd_logit_scale

(self, value: float)

gguf-py/gguf/gguf_writer.py:814

↓ 5 callersMethodadd_name

(self, name: str)

gguf-py/gguf/gguf_writer.py:550

↓ 5 callersMethodadd_pad_token_id

(self, id: int)

gguf-py/gguf/gguf_writer.py:1081

↓ 5 callersMethodadd_rule

common/peg-parser.cpp:316

↓ 5 callersMethodaddr

src/llama-mmap.cpp:616

↓ 5 callersFunctionalign_with_offset

tests/test-quantize-perf.cpp:74

↓ 5 callersFunctionaligned_offset

ggml/src/ggml-alloc.c:52

↓ 5 callersFunctionall_kv_in_other

tests/test-gguf.cpp:950

↓ 5 callersFunctionapir_decode_ggml_buffer_type

ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:70

↓ 5 callersFunctionapir_decoder_read

ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:116

↓ 5 callersFunctionapir_encode_apir_buffer_type_host_handle

ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:78

↓ 5 callersFunctionapir_encode_uint32_t

ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:246

↓ 5 callersMethodas_repr

Note: only for debugging purposes

common/jinja/value.h:162

↓ 5 callersFunctionatomic_fetch_add

ggml/src/ggml-cpu/ggml-cpu.c:133

↓ 5 callersFunctionbasename

ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:243

↓ 5 callersFunctionbenchmark_function

tests/test-quantize-perf.cpp:79

↓ 5 callersMethodbpe

(mergeable_ranks: dict[bytes, int], token: bytes, max_rank: int | None = None)

convert_hf_to_gguf.py:3785

← previous next →1,301–1,400 of 13,473, ranked by callers