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 callersMethodadd_audio_stack_factor
(self, value: int)
gguf-py/gguf/gguf_writer.py:1284
↓ 4 callersMethodadd_int32
(self, key: str, val: int)
gguf-py/gguf/gguf_writer.py:298
↓ 4 callersMethodadd_kv_lora_rank
(self, length: int)
gguf-py/gguf/gguf_writer.py:928
↓ 4 callersMethodadd_num_deepstack_layers
(self, count: int)
gguf-py/gguf/gguf_writer.py:979
↓ 4 callersMethodadd_q_lora_rank
(self, length: int)
gguf-py/gguf/gguf_writer.py:925
↓ 4 callersMethodadd_rope_scaling_yarn_log_mul
(self, value: float)
gguf-py/gguf/gguf_writer.py:1012
↓ 4 callersMethodadd_ssm_group_count
(self, value: int)
gguf-py/gguf/gguf_writer.py:1039
↓ 4 callersMethodadd_tensor
( self, name: str, tensor: np.ndarray[Any, Any], raw_shape: Sequence[int] | None = None, raw_d
gguf-py/gguf/gguf_writer.py:375
↓ 4 callersMethodadd_tensor_data_layout
(self, layout: str)
gguf-py/gguf/gguf_writer.py:676
↓ 4 callersMethodadd_token_type_count
(self, value: int)
gguf-py/gguf/gguf_writer.py:1063
↓ 4 callersMethodadd_type
(self, type_name: str)
gguf-py/gguf/gguf_writer.py:496
↓ 4 callersMethodadd_wkv_head_size
(self, size: int)
gguf-py/gguf/gguf_writer.py:889
↓ 4 callersFunctionall_greater_f32
ggml/src/ggml-hexagon/htp/argsort-ops.c:27
↓ 4 callersFunctionapir_decode_array_size_unchecked
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:227
↓ 4 callersFunctionapir_decode_ggml_tensor
ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:38
↓ 4 callersFunctionapir_decode_virtgpu_shmem_res_id
ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:138
↓ 4 callersFunctionapir_encode_array_size
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:212
↓ 4 callersFunctionapir_encode_ggml_tensor
ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:32
↓ 4 callersFunctionapir_encode_int32_t
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:190
↓ 4 callersFunctionapir_encode_virtgpu_shmem_res_id
ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h:134
↓ 4 callersFunctionapply_transform
common/jinja/string.cpp:116
↓ 4 callersFunctionassert_msg_equals
tests/test-chat.cpp:362
↓ 4 callersFunctionasync_dpct_memcpy
ggml/src/ggml-sycl/dpct/helper.hpp:1808
↓ 4 callersFunctionbest_index_int8
ggml/src/ggml-quants.c:24
↓ 4 callersFunctionbest_index_mxfp4
ggml/src/ggml-quants.c:295
↓ 4 callersMethodbuild
common/peg-parser.cpp:1262
↓ 4 callersFunctionbuild_grammar_with_root
tests/test-grammar-integration.cpp:18
↓ 4 callersFunctionbuild_rs_inp_impl
src/llama-graph.cpp:2615
↓ 4 callersFunctionbuild_tool_call
Helper to create a tool call with arguments as JSON object
tools/parser/template-analysis.cpp:181
↓ 4 callersFunctionbytes_from_nibbles_32
Unpack 32 4-bit fields into 32 bytes The output vector contains 32 bytes, each one in [ 0 .. 15 ] interval
ggml/src/ggml-cpu/arch/loongarch/quants.c:399
↓ 4 callersFunctionbytes_from_nibbles_32
ggml/src/ggml-cpu/amx/mmq.cpp:520
↓ 4 callersFunctionbytes_to_unicode
Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control characters the bpe code bar
gguf-py/gguf/vocab.py:637
↓ 4 callersMethodcallTool
* Execute a tool call on a connection. * Supports abort signal for cancellable operations (e.g., when user stops generation). * Formats the raw to
tools/server/webui/src/lib/services/mcp.service.ts:804
↓ 4 callersMethodcancelPreEncode
()
tools/server/webui/src/lib/stores/chat.svelte.ts:1640
↓ 4 callersMethodcascade
common/preset.cpp:459
↓ 4 callersMethodclone
tools/mtmd/mtmd.cpp:58
↓ 4 callersFunctioncommon_chat_format_name
common/chat.cpp:680
↓ 4 callersFunctioncommon_chat_msgs_to_json_oaicompat
DEPRECATED: only used in tests
common/chat.cpp:393
↓ 4 callersFunctioncommon_embd_normalize
common/common.cpp:1651
↓ 4 callersFunctioncommon_http_client
common/http.h:68
↓ 4 callersFunctioncommon_log_pause
common/log.cpp:381
↓ 4 callersFunctioncommon_params_handle_model
common/arg.cpp:333
↓ 4 callersFunctioncommon_sampler_clone
common/sampling.cpp:463
↓ 4 callersFunctioncommon_sampler_reset
common/sampling.cpp:455
↓ 4 callersFunctioncompute_2d_workgroups
Return a rectangular grid of workgroups with minimal over-provisioned workgroups. Assumes that the total number of workgroups does not exceed max_per_
ggml/src/ggml-webgpu/ggml-webgpu.cpp:40
↓ 4 callersFunctionconvert
ggml/src/ggml-sycl/set_rows.cpp:16
↓ 4 callersFunctionconvert_less_than_thousand
Convert a number less than 1000 to words
tools/tts/tts.cpp:296
↓ 4 callersFunctioncore_dot_chunk_fp16
requires external HMX lock
ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c:674
↓ 4 callersFunctioncpuid
common/common.cpp:138
↓ 4 callersMethodcpy_k
src/llama-kv-cache.cpp:1196
↓ 4 callersFunctioncreate_completion
Calls the /completion API on llama-server. See https://github.com/ggml-org/llama.cpp/tree/HEAD/tools/server#api-endpoints
examples/pydantic_models_to_grammar_examples.py:22
↓ 4 callersFunctioncreate_ov_output_tensor
ggml/src/ggml-openvino/utils.cpp:65
↓ 4 callersFunctioncreate_tools
tests/test-chat-peg-parser.cpp:46
↓ 4 callersFunctiondecode_utf8
NOTE: assumes valid utf8 (but checks for overrun)
src/llama-grammar.cpp:19
↓ 4 callersMethoddeleteMessage
(messageId: string)
tools/server/webui/src/lib/stores/chat.svelte.ts:1061
↓ 4 callersMethoddevice_count
ggml/src/ggml-sycl/dpct/helper.hpp:887
↓ 4 callersMethoddoes_token_look_special
(self, token: str | bytes)
convert_hf_to_gguf.py:1219
↓ 4 callersFunctiondot
"Scalar" dot product between the quantized vector x and float vector y
pocs/vdot/vdot.cpp:62
↓ 4 callersMethoddouble_quoted_string
common/peg-parser.cpp:1273
↓ 4 callersFunctiondpct_memcpy
ggml/src/ggml-sycl/dpct/helper.hpp:1421
↓ 4 callersFunctiondsv4_view_state_segment
src/models/deepseek4.cpp:216
↓ 4 callersFunctiondsv4_zero_cache_rows
src/llama-memory-hybrid-iswa.cpp:81
↓ 4 callersFunctionescape_json_string_inner
JSON-escape a string and return the inner content (without surrounding quotes).
common/chat-peg-parser.cpp:70
↓ 4 callersFunctionexit_with_warning
(message, model_path)
examples/model-conversion/scripts/utils/common.py:280
↓ 4 callersMethodextractServerDefaults
* Extract server default parameters that can be synced from `/props` response. * Handles both generation settings parameters and webui-specific sett
tools/server/webui/src/lib/services/parameter-sync.service.ts:286
↓ 4 callersFunctionfetch_or_cached
Try cache first, then fetch and parse a single GGUF shard.
tests/gguf-model-data.cpp:573
↓ 4 callersMethodfill_sin_cos_table
tools/mtmd/mtmd-audio.cpp:17
↓ 4 callersFunctionfindLeafNode
(messages: readonly DatabaseMessage[], messageId: string)
tools/server/webui/src/lib/utils/branching.ts:99
↓ 4 callersMethodfind_aparam
(self, keys: Iterable[str], optional: bool = False)
convert_hf_to_gguf.py:2279
↓ 4 callersMethodflush
(self)
gguf-py/gguf/gguf_writer.py:485
↓ 4 callersFunctionformatDiagnosticErrorMessage
(error: unknown)
tools/server/webui/src/lib/utils/request-helpers.ts:87
↓ 4 callersMethodformat_enum_value
Format a value as an enum if possible.
gguf-py/gguf/scripts/gguf_editor_gui.py:1052
↓ 4 callersFunctionformat_multiline_description
Format a multiline description with proper indentation. Args: description (str): Multiline description. indent_level (int):
examples/pydantic_models_to_grammar.py:966
↓ 4 callersFunctionformat_size
(size_bytes: int)
examples/model-conversion/scripts/utils/inspect-org-model.py:87
↓ 4 callersFunctionfp32_to_bits
ggml/src/ggml-impl.h:375
↓ 4 callersFunctionfrand
tests/test-rope.cpp:51
↓ 4 callersMethodfree_buffer
ggml/src/ggml-rpc/ggml-rpc.cpp:985
↓ 4 callersMethodfromCode
examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:32
↓ 4 callersMethodfrom_eager
(cls, t: Any)
gguf-py/gguf/lazy.py:196
↓ 4 callersFunctionfrom_json
common/jinja/value.cpp:1256
↓ 4 callersFunctiongemm_batch
Computes a batch of matrix-matrix product with general matrices. \param [in] q The queue where the routine should be executed. \param [in] a_trans Spe
ggml/src/ggml-sycl/dpct/helper.hpp:2423
↓ 4 callersFunctiongenerate_gbnf_grammar_and_documentation
Generate GBNF grammar and documentation for a list of Pydantic models. Args: pydantic_model_list: List of Pydantic model classes.
examples/pydantic_models_to_grammar.py:1065
↓ 4 callersMethodget
* @brief Get the device buffer pointer. * * @return Pointer to the allocated buffer, or nullptr if not allocated. */
ggml/src/ggml-cann/ggml-cann.cpp:1218
↓ 4 callersFunctiongetAuthHeaders
()
tools/server/webui/src/lib/utils/api-headers.ts:9
↓ 4 callersFunctiongetJsonHeaders
()
tools/server/webui/src/lib/utils/api-headers.ts:19
↓ 4 callersFunctiongetMessageSiblings
( messages: readonly DatabaseMessage[], messageId: string )
tools/server/webui/src/lib/utils/branching.ts:163
↓ 4 callersFunctiongetRequestUrl
(input: RequestInfo | URL)
tools/server/webui/src/lib/utils/request-helpers.ts:12
↓ 4 callersFunctiongetUploadedFileCategory
* Gets the file type category from an uploaded file, checking both MIME type and extension * @param uploadedFile - The uploaded file to check * @ret
tools/server/webui/src/lib/utils/attachment-type.ts:9
↓ 4 callersMethodget_add_bos
src/llama-vocab.cpp:3729
↓ 4 callersMethodget_add_eos
src/llama-vocab.cpp:3733
↓ 4 callersFunctionget_all_kv_cache_types
common/arg.cpp:405
↓ 4 callersFunctionget_cache_acl_tensor
* @brief Get or expand a cached tensor filled with a scalar value. * * This function manages cached device memory for tensors. If the current * cac
ggml/src/ggml-cann/aclnn_ops.cpp:1008
↓ 4 callersFunctionget_copy_range
Get actual copy range and make sure it will not exceed range.
ggml/src/ggml-sycl/dpct/helper.hpp:1433
↓ 4 callersMethodget_embd_pooled
src/llama-graph.h:646
↓ 4 callersMethodget_enabled_functions
Get all enabled functions with their metadata.
ggml/src/ggml-virtgpu/regenerate_remoting.py:94
↓ 4 callersFunctionget_int_from_int8
ggml/src/ggml-sycl/vecdotq.hpp:48
↓ 4 callersMethodget_kq_mask
src/llama-graph.h:345
↓ 4 callersFunctionget_kv_types
tests/test-gguf.cpp:133
↓ 4 callersMethodget_llama_context
tools/server/server-context.cpp:3107
↓ 4 callersMethodget_logits
src/llama-context.cpp:784
← previousnext →1,601–1,700 of 13,473, ranked by callers