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

↓ 4 callersMethodhas_kv

src/llama-hparams.cpp:239

↓ 4 callersMethodhead

src/llama-kv-cache.h:45

↓ 4 callersFunctionhex_dump_f16_line

ggml/src/ggml-hexagon/htp/hex-dump.h:42

↓ 4 callersFunctionhex_dump_f32_line

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

↓ 4 callersFunctionhmx_add_overflow

ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:109

↓ 4 callersFunctionhmx_compute_chunks

Search for optimal (mc, nc) chunk sizes within VTCM budget. VTCM model: nc * per_n_cost + mc * per_m_cost + mc * nc * per_mn_cost + overhead Minimiz

ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:130

↓ 4 callersFunctionhmx_init_column_scales

Initialise aligned 256-byte area with scale vector + zero padding.

ggml/src/ggml-hexagon/htp/hmx-utils.h:18

↓ 4 callersFunctionhvx_copy_f32_uu

copy n fp32 elements : source is unaligned, destination unaligned

ggml/src/ggml-hexagon/htp/hvx-copy.h:128

↓ 4 callersFunctionhvx_vec_abs_f16

ggml/src/ggml-hexagon/htp/hvx-base.h:80

↓ 4 callersFunctionhvx_vec_abs_f32

ggml/src/ggml-hexagon/htp/hvx-base.h:92

↓ 4 callersFunctionhvx_vec_inverse_f32

ggml/src/ggml-hexagon/htp/hvx-inverse.h:89

↓ 4 callersFunctionincr_ptr_aligned

ggml/src/ggml-cpu/ggml-cpu.c:1507

↓ 4 callersFunctioninit_fastdiv_values

ggml/src/ggml-sycl/common.hpp:703

↓ 4 callersFunctioninit_set_rows_row_ids

tests/test-backend-ops.cpp:2276

↓ 4 callersMethodinvoke

common/jinja/value.h:138

↓ 4 callersFunctioniq3_data_index

ggml/src/ggml-quants.c:3568

↓ 4 callersFunctioniq3_find_best_neighbour

ggml/src/ggml-quants.c:3746

↓ 4 callersFunctionisValidModelName

(modelName: string)

tools/server/webui/src/lib/utils/model-names.ts:54

↓ 4 callersMethodis_child

tools/server/server-task.h:257

↓ 4 callersFunctionis_digit_char

src/llama-grammar.cpp:94

↓ 4 callersMethodis_empty

Returns true when all unaligned pipelines are null. We only check for unaligned variants since one of the unaligned pipelines must exist while aligned

ggml/src/ggml-vulkan/ggml-vulkan.cpp:169

↓ 4 callersFunctionis_matmul_weight

* @brief Check whether a tensor is a weight tensor for matrix multiplication. * * @details Checks whether the given tensor serves as weight parame

ggml/src/ggml-cann/aclnn_ops.h:932

↓ 4 callersFunctionisinf_or_max

accept FLT_MAX as infinity

tests/test-backend-ops.cpp:453

↓ 4 callersFunctionkleidiai_collect_kernel_chain

ggml/src/ggml-cpu/kleidiai/kleidiai.cpp:394

↓ 4 callersFunctionkleidiai_is_weight_header_valid

ggml/src/ggml-cpu/kleidiai/kleidiai.cpp:325

↓ 4 callersFunctionkv_cache_type_from_str

common/arg.cpp:396

↓ 4 callersFunctionlasx_extracti128_lo

Convert __m256i low part to __m128i

ggml/src/ggml-cpu/arch/loongarch/quants.c:179

↓ 4 callersFunctionllama_chat_builtin_templates

src/llama-chat.cpp:932

↓ 4 callersFunctionllama_expert_gating_func_name

src/llama-model.cpp:508

↓ 4 callersFunctionllama_format_tensor_shape

src/llama-impl.cpp:101

↓ 4 callersFunctionllama_ftype_get_default_type

src/llama-quant.cpp:792

↓ 4 callersFunctionllama_ftype_to_name

tests/test-quant-type-selection.cpp:71

↓ 4 callersFunctionllama_get_embeddings_ith

src/llama-context.cpp:3149

↓ 4 callersFunctionllama_get_sampled_candidates_ith

src/llama-context.cpp:3183

↓ 4 callersFunctionllama_grammar_accept

src/llama-grammar.cpp:1042

↓ 4 callersFunctionllama_grammar_accept_token

src/llama-grammar.cpp:1456

↓ 4 callersFunctionllama_grammar_reject_candidates_for_stack

src/llama-grammar.cpp:1053

↓ 4 callersFunctionllama_max_tensor_buft_overrides

src/llama.cpp:61

↓ 4 callersFunctionllama_memory_seq_pos_min

src/llama-context.cpp:3325

↓ 4 callersFunctionllama_model_decoder_start_token

src/llama-model.cpp:9656

↓ 4 callersFunctionllama_model_get_device

src/llama-model.cpp:9684

↓ 4 callersFunctionllama_model_load_from_file_impl

src/llama.cpp:171

↓ 4 callersFunctionllama_model_n_layer

src/llama-model.cpp:9347

↓ 4 callersFunctionllama_n_ctx_seq

src/llama-context.cpp:3056

↓ 4 callersFunctionllama_quant_free

src/llama-quant.cpp:1328

↓ 4 callersFunctionllama_sampler_clone

src/llama-sampler.cpp:397

↓ 4 callersFunctionllama_sampler_init_grammar_impl

src/llama-sampler.cpp:2532

↓ 4 callersFunctionllama_sampler_init_llg

common/llguidance.cpp:219

↓ 4 callersFunctionllama_sampler_init_typical

src/llama-sampler.cpp:1780

↓ 4 callersFunctionllama_sampler_init_xtc

src/llama-sampler.cpp:2188

↓ 4 callersFunctionllama_set_causal_attn

src/llama-context.cpp:3111

↓ 4 callersFunctionllama_state_load_file

src/llama-context.cpp:3399

↓ 4 callersFunctionllama_supports_rpc

src/llama.cpp:79

↓ 4 callersFunctionllama_token_data_array_partial_sort_inplace

reduces the size of cur_p to npartial, keeping only the top npartial elements

src/llama-sampler.cpp:193

↓ 4 callersFunctionllama_vocab_fim_mid

src/llama-vocab.cpp:3947

↓ 4 callersFunctionllama_vocab_fim_pre

src/llama-vocab.cpp:3939

↓ 4 callersFunctionllama_vocab_fim_rep

src/llama-vocab.cpp:3955

↓ 4 callersFunctionllama_vocab_fim_suf

src/llama-vocab.cpp:3943

↓ 4 callersFunctionlora_all_alora

tools/server/server-common.cpp:103

↓ 4 callersFunctionlsx_packs_h

ggml/src/ggml-cpu/arch/loongarch/quants.c:35

↓ 4 callersFunctionmake_generic_stringstream

ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:247

↓ 4 callersMethodmap_tensor_name

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

convert_hf_to_gguf.py:9720

↓ 4 callersMethodmerge

common/preset.cpp:160

↓ 4 callersMethodmeta_with_dtype_and_shape

(cls, dtype: torch.dtype, shape: tuple[int, ...])

convert_hf_to_gguf.py:13907

↓ 4 callersMethodmeta_with_dtype_and_shape

(cls, dtype: Any, shape: Any)

gguf-py/gguf/lazy.py:193

↓ 4 callersFunctionmode_to_str

common/chat-diff-analyzer.cpp:158

↓ 4 callersMethodmodelSupportsVision

* Check if a model supports vision modality

tools/server/webui/src/lib/stores/models.svelte.ts:154

↓ 4 callersFunctionmove_to_line_start

common/console.cpp:529

↓ 4 callersFunctionmtmd_context_params_default

tools/mtmd/mtmd.cpp:122

↓ 4 callersFunctionmtmd_default_marker

tools/mtmd/mtmd.cpp:109

↓ 4 callersFunctionmtmd_image_tokens_get_n_tokens

tools/mtmd/mtmd.cpp:1283

↓ 4 callersFunctionmul_sum_i8_pairs

multiply int8_t, add results pairwise twice

ggml/src/ggml-cpu/arch/loongarch/quants.c:110

↓ 4 callersFunctionmul_sum_i8_pairs

multiply int8_t, add results pairwise twice

ggml/src/ggml-cpu/arch/x86/quants.c:30

↓ 4 callersFunctionmul_sum_i8_pairs_float

multiply int8_t, add results pairwise twice and return as float vector

ggml/src/ggml-cpu/arch/x86/quants.c:122

↓ 4 callersFunctionmul_sum_us8_pairs_float

ggml/src/ggml-cpu/arch/x86/quants.c:105

↓ 4 callersFunctionmxfp4_convert_scales

ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:327

↓ 4 callersMethodn_embd_v_gqa_max

src/llama-hparams.cpp:146

↓ 4 callersFunctionparallel_for_ggml

ggml/src/ggml-cpu/amx/common.h:99

↓ 4 callersFunctionparse_cpu_range

common/common.cpp:290

↓ 4 callersMethodpop

ggml/src/ggml-hexagon/ggml-hexagon.cpp:1836

↓ 4 callersFunctionpop_cursor

common/console.cpp:265

↓ 4 callersMethodpop_front

common/sampling.cpp:63

↓ 4 callersFunctionpostprocess_cpu_params

common/common.cpp:266

↓ 4 callersMethodpreprocess

tools/mtmd/mtmd-image.cpp:568

↓ 4 callersFunctionprint_fail

scripts/server-test-function-call.py:69

↓ 4 callersFunctionprint_ok

tests/test-opt.cpp:174

↓ 4 callersFunctionprint_usage

examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp:804

↓ 4 callersFunctionprocess_weight_tensor

ggml/src/ggml-openvino/ggml-quants.cpp:676

↓ 4 callersMethodpush

ggml/src/ggml-hexagon/ggml-hexagon.cpp:1773

↓ 4 callersMethodpush_back

common/jinja/value.h:371

↓ 4 callersMethodquantize

(self, data: np.ndarray, qtype: GGMLQuantizationType)

gguf-py/tests/test_quants.py:105

↓ 4 callersMethodquantize

(cls, tensor: np.ndarray | LazyNumpyTensor)

gguf-py/gguf/quants.py:188

↓ 4 callersFunctionrandom_string

Helper to generate random string

tests/test-jinja.cpp:2099

↓ 4 callersMethodread_tensor_data

tools/export-lora/export-lora.cpp:95

↓ 4 callersMethodreduce

ggml/src/ggml-sycl/common.hpp:902

↓ 4 callersMethodrelease

ggml/src/ggml-hexagon/ggml-hexagon.cpp:2106

↓ 4 callersFunctionres_ok

tools/server/server-models.cpp:884

↓ 4 callersFunctionrm_leading_dashes

common/preset.cpp:11

↓ 4 callersMethodrun

examples/pydantic_models_to_grammar_examples.py:89

↓ 4 callersFunctionrun_adb_command

(cmd: str, *, check: bool = True)

scripts/snapdragon/qdc/tests/utils.py:41

← previous next →1,801–1,900 of 13,473, ranked by callers