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

↓ 3 callersFunctionavg
tools/llama-bench/llama-bench.cpp:100
↓ 3 callersFunctionbalance211
ggml/src/ggml-cpu/amx/common.h:37
↓ 3 callersFunctionbase64_decode
tools/server/server-common.cpp:181
↓ 3 callersFunctionbatch_process
examples/retrieval/retrieval.cpp:85
↓ 3 callersMethodbench
tests/testing.h:145
↓ 3 callersFunctionbinary_op
ggml/src/ggml-cpu/binary-ops.cpp:116
↓ 3 callersMethodbool
examples/llama.android/lib/src/main/java/com/arm/aichat/internal/gguf/GgufMetadataReaderImpl.kt:197
↓ 3 callersMethodbos_token
(self)
gguf-py/gguf/vocab.py:804
↓ 3 callersFunctionbuildProxiedUrl
(targetUrl: string)
tools/server/webui/src/lib/utils/cors-proxy.ts:13
↓ 3 callersMethodbuild_graph
src/llama-model.cpp:8765
↓ 3 callersMethodbuild_input_k_rot
src/llama-kv-cache.cpp:1313
↓ 3 callersMethodbuild_input_v_rot
src/llama-kv-cache.cpp:1334
↓ 3 callersFunctionbuild_repetition
common/json-schema-to-grammar.cpp:17
↓ 3 callersFunctionbuild_test_tools
Helper to build tools definition for tests
tests/test-chat-auto-parser.cpp:1501
↓ 3 callersMethodcast
ggml/src/gguf.cpp:205
↓ 3 callersFunctioncategory_is_attn_v
check if category is for attention-v-like tensors (more sensitive to quantization)
src/llama-quant.cpp:153
↓ 3 callersFunctioncausal_conv1d
Causal Conv1d function for Q,K,V When qkv is 0, it is Q, 1 is K, 2 is V
src/models/kimi-linear.cpp:7
↓ 3 callersFunctionchat_add_and_format
examples/llama.android/lib/src/main/cpp/ai_chat.cpp:289
↓ 3 callersFunctioncheck_allow_gpu_index
device_index: device index from 0 to n (continue numbers). It is used for device select/set in SYCL backend internal data structure. */
ggml/src/ggml-sycl/ggml-sycl.cpp:317
↓ 3 callersMethodcleanup
()
tools/server/webui/src/lib/utils/audio-recording.ts:114
↓ 3 callersMethodclearActiveConversation
* Clears the active conversation and messages.
tools/server/webui/src/lib/stores/conversations.svelte.ts:307
↓ 3 callersMethodclear_model_weights
ggml/src/ggml-openvino/ggml-decoder.h:191
↓ 3 callersFunctionclip_image_batch_encode
tools/mtmd/clip.cpp:3124
↓ 3 callersFunctionclip_image_encode
tools/mtmd/clip.cpp:3115
↓ 3 callersFunctioncommon_chat_format_example
common/chat.cpp:510
↓ 3 callersFunctioncommon_chat_format_single
common/chat.cpp:480
↓ 3 callersFunctioncommon_chat_peg_parse
common/chat.cpp:2309
↓ 3 callersFunctioncommon_chat_templates_get_caps
common/chat.cpp:2382
↓ 3 callersFunctioncommon_chat_templates_was_explicit
common/chat.cpp:543
↓ 3 callersFunctioncommon_chat_tools_parse_oaicompat
common/chat.cpp:419
↓ 3 callersFunctioncommon_chat_tools_to_json_oaicompat
common/chat.cpp:400
↓ 3 callersFunctioncommon_context_can_seq_rm
common/common.cpp:1401
↓ 3 callersFunctioncommon_download_file_single
common/download.cpp:470
↓ 3 callersFunctioncommon_download_model
common/download.cpp:757
↓ 3 callersFunctioncommon_download_split_repo_tag
common/download.cpp:108
↓ 3 callersFunctioncommon_embd_similarity_cos
common/common.cpp:1687
↓ 3 callersFunctioncommon_fit_params
common/fit.cpp:758
↓ 3 callersFunctioncommon_get_model_endpoint
common/common.cpp:1386
↓ 3 callersFunctioncommon_ggml_ne_string
common/debug.cpp:9
↓ 3 callersFunctioncommon_log_set_colors
common/log.cpp:404
↓ 3 callersFunctioncommon_ngram_cache_draft
common/ngram-cache.cpp:146
↓ 3 callersFunctioncommon_ngram_cache_merge
common/ngram-cache.cpp:260
↓ 3 callersFunctioncommon_ngram_cache_save
common/ngram-cache.cpp:200
↓ 3 callersFunctioncommon_ngram_map_hash
Compute the LCG hash of a n-gram of size len at offset start.
common/ngram-map.cpp:14
↓ 3 callersFunctioncommon_reasoning_budget_init_state
common/reasoning-budget.cpp:194
↓ 3 callersFunctioncommon_reasoning_format_from_name
common/chat.cpp:710
↓ 3 callersFunctioncommon_replay_last_token
common/common.cpp:1902
↓ 3 callersFunctioncommon_sampler_get
common/sampling.cpp:520
↓ 3 callersFunctioncommon_sampler_print
common/sampling.cpp:686
↓ 3 callersFunctioncommon_sampler_types_from_names
common/sampling.cpp:753
↓ 3 callersFunctioncompare_tensors
(t1: np.ndarray, t2: np.ndarray, qtype: GGMLQuantizationType)
gguf-py/tests/test_quants.py:117
↓ 3 callersFunctioncompare_tokens
(original, converted, type_suffix="", output_dir="data")
examples/model-conversion/scripts/utils/common.py:208
↓ 3 callersFunctioncompute_logprobs
tools/perplexity/perplexity.cpp:700
↓ 3 callersMethodconvertDbMessageToApiChatMessageData
* Converts a database message with attachments to API chat message format. * Processes various attachment types (images, text files, PDFs) and forma
tools/server/webui/src/lib/services/chat.service.ts:727
↓ 3 callersFunctionconvertPDFToText
(file: File)
tools/server/webui/src/lib/utils/pdf-processing.ts:53
↓ 3 callersMethodcreateAssistantMessage
(parentId?: string)
tools/server/webui/src/lib/stores/chat.svelte.ts:444
↓ 3 callersMethodcreateListChangedHandlers
(serverName: string)
tools/server/webui/src/lib/stores/mcp.svelte.ts:692
↓ 3 callersMethodcreateRootMessage
* Creates a root message for a new conversation. * Root messages are not displayed but serve as the tree root for branching. * * @param convId -
tools/server/webui/src/lib/services/database.service.ts:113
↓ 3 callersMethodcreate_state
the task will be moved into queue, then onto slots however, the state must be kept by caller (e.g., HTTP thread)
tools/server/server-task.h:249
↓ 3 callersMethoddecode_tokens
tests/test-backend-sampler.cpp:222
↓ 3 callersMethoddequant_model
(self)
convert_hf_to_gguf.py:285
↓ 3 callersFunctionderiveSingleTurnSections
* Derives display sections from a single assistant message and its direct tool results. * * @param message - The assistant message * @param toolMes
tools/server/webui/src/lib/utils/agentic.ts:38
↓ 3 callersFunctiondl_get_sym
ggml/src/ggml-backend-dl.cpp:17
↓ 3 callersFunctiondownload_file
Download a file from a URL to a local path. If the file already exists, it will not be downloaded again. output_file_path is the local path
tools/server/tests/utils.py:651
↓ 3 callersFunctiondsv4_add_scalar
src/models/deepseek4.cpp:170
↓ 3 callersFunctiondsv4_arange_i32
src/models/deepseek4.cpp:186
↓ 3 callersFunctiondsv4_cache_view_3d
src/models/deepseek4.cpp:907
↓ 3 callersFunctiondsv4_mul_scalar
src/models/deepseek4.cpp:178
↓ 3 callersFunctiondsv4_softmax_pool_ratio
src/models/deepseek4.cpp:438
↓ 3 callersMethodeager_to_meta
(cls, t: Any)
gguf-py/gguf/lazy.py:187
↓ 3 callersFunctionenable_adreno_trans_weight
ggml/src/ggml-opencl/ggml-opencl.cpp:4591
↓ 3 callersMethodeos_token
(self)
gguf-py/gguf/vocab.py:808
↓ 3 callersFunctioneval_message
tools/mtmd/mtmd-cli.cpp:231
↓ 3 callersFunctionexec_statements
common/jinja/runtime.cpp:21
↓ 3 callersMethodext_set
src/llama-kv-cells.h:405
↓ 3 callersFunctionfastdiv
ggml/src/ggml-sycl/common.hpp:752
↓ 3 callersFunctionfastmodulo
ggml/src/ggml-sycl/common.hpp:875
↓ 3 callersMethodfetchModelProps
* Fetch props for a specific model from /props endpoint * Uses caching to avoid redundant requests * * In ROUTER mode, this will only fetch prop
tools/server/webui/src/lib/stores/models.svelte.ts:354
↓ 3 callersMethodfetchRouterModels
* Fetch router models with full metadata (ROUTER mode only) * This fetches the /models endpoint which returns status info for each model
tools/server/webui/src/lib/stores/models.svelte.ts:323
↓ 3 callersMethodfill_hann_window
tools/mtmd/mtmd-audio.cpp:27
↓ 3 callersMethodfill_mel_filterbank_matrix
tools/mtmd/mtmd-audio.cpp:35
↓ 3 callersFunctionfinalize_file
common/hf-cache.cpp:462
↓ 3 callersMethodfindServerForUri
* Find server name for a resource URI
tools/server/webui/src/lib/stores/mcp-resources.svelte.ts:507
↓ 3 callersFunctionfmt_size
ggml/src/ggml-backend.cpp:935
↓ 3 callersFunctionforeach_function
Helper to iterate over tools/functions
common/chat-auto-parser-generator.cpp:17
↓ 3 callersFunctionformat_anthropic_sse
tools/server/server-common.cpp:1384
↓ 3 callersMethodformat_field_value
(self, field: ReaderField)
gguf-py/gguf/scripts/gguf_editor_gui.py:1062
↓ 3 callersFunctionformat_literal
common/json-schema-to-grammar.cpp:302
↓ 3 callersFunctionformat_oai_sse
format server-sent event (SSE), return the formatted string to send note: if data is a json array, it will be sent as multiple events, one per item
tools/server/server-common.cpp:1347
↓ 3 callersFunctionformat_variants
()
scripts/get_chat_template.py:51
↓ 3 callersFunctionfs_get_cache_file
common/common.cpp:986
↓ 3 callersFunctionfs_validate_filename
Validate if a filename is safe to use To validate a full path, split the path by the OS-specific path separator, and validate each part with this func
common/common.cpp:763
↓ 3 callersMethodfunc
(modelcls: AnyModel)
convert_hf_to_gguf.py:1004
↓ 3 callersFunctiongenerate_gbnf_grammar
Generate GBnF Grammar Generates a GBnF grammar for a given model. :param model: A Pydantic model class to generate the grammar for. Mu
examples/pydantic_models_to_grammar.py:442
↓ 3 callersFunctiongenerate_gbnf_grammar_from_pydantic_models
Generate GBNF Grammar from Pydantic Models. This method takes a list of Pydantic models and uses them to generate a GBNF grammar string. The
examples/pydantic_models_to_grammar.py:528
↓ 3 callersFunctiongenerate_markdown_documentation
Generate markdown documentation for a list of Pydantic models. Args: pydantic_models (list[type[BaseModel]]): list of Pydantic model
examples/pydantic_models_to_grammar.py:676
↓ 3 callersMethodgetAllConversations
* Gets all conversations, sorted by last modified time (newest first). * * @returns Array of conversations
tools/server/webui/src/lib/services/database.service.ts:289
↓ 3 callersMethodgetApiOptions
()
tools/server/webui/src/lib/stores/chat.svelte.ts:1565
↓ 3 callersMethodgetConversation
* Gets a conversation by ID. * * @param id - Conversation ID * @returns The conversation if found, otherwise undefined
tools/server/webui/src/lib/services/database.service.ts:299
↓ 3 callersFunctiongetFileTypeCategoryByExtension
(filename: string)
tools/server/webui/src/lib/utils/file-type.ts:94
← previousnext →2,001–2,100 of 13,473, ranked by callers