Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/antirez/llama.cpp-deepseek-v4-flash
/ functions
Functions
13,473 in github.com/antirez/llama.cpp-deepseek-v4-flash
⨍
Functions
13,473
◇
Types & classes
3,460
↳
Endpoints
3
↓ 4 callers
Method
s_copy
src/llama-memory-recurrent.cpp:1161
↓ 4 callers
Method
seq_count
number of different sequences in the cell
src/llama-kv-cells.h:293
↓ 4 callers
Method
setStreamingActive
(active: boolean)
tools/server/webui/src/lib/stores/chat.svelte.ts:149
↓ 4 callers
Method
set_colors
common/log.cpp:327
↓ 4 callers
Method
set_filter
tests/testing.h:46
↓ 4 callers
Function
should_stop
tools/cli/cli.cpp:39
↓ 4 callers
Function
show_additional_info
tools/mtmd/debug/mtmd-debug.cpp:21
↓ 4 callers
Method
single_quoted_string
common/peg-parser.cpp:1279
↓ 4 callers
Method
split_seq
src/llama-batch.cpp:613
↓ 4 callers
Method
stopInterval
* Stops the auto-scroll interval.
tools/server/webui/src/lib/hooks/use-auto-scroll.svelte.ts:151
↓ 4 callers
Method
stories15m_moe
()
tools/server/tests/utils.py:542
↓ 4 callers
Function
string_repeat
common/common.cpp:494
↓ 4 callers
Function
string_starts_with
remove when moving to c++20
common/common.h:744
↓ 4 callers
Function
string_starts_with
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:207
↓ 4 callers
Function
sum_i16_pairs_float
add int16_t pairwise and return as float vector
ggml/src/ggml-cpu/arch/x86/quants.c:99
↓ 4 callers
Method
summary
Print summary and return an exit code
tests/testing.h:235
↓ 4 callers
Method
supportsResources
* Check if a connection supports resources. * Per MCP spec: presence of the `resources` key (even as empty object `{}`) indicates support. * Empty
tools/server/webui/src/lib/services/mcp.service.ts:1095
↓ 4 callers
Method
supports_op
ggml/src/ggml-cpu/repack.cpp:4774
↓ 4 callers
Function
tensor_to_float
tests/test-backend-ops.cpp:231
↓ 4 callers
Function
test_build_grammar_fails
tests/test-grammar-integration.cpp:26
↓ 4 callers
Function
test_top_k
tests/test-sampling.cpp:86
↓ 4 callers
Function
test_top_p
tests/test-sampling.cpp:97
↓ 4 callers
Function
test_xtc
tests/test-sampling.cpp:119
↓ 4 callers
Function
tokenize
(content)
tools/server/chat.mjs:63
↓ 4 callers
Function
tokenize_input_prompts
tools/server/server-common.cpp:793
↓ 4 callers
Method
tool_arg
common/chat-peg-parser.h:85
↓ 4 callers
Method
tool_arg_close
common/chat-peg-parser.h:87
↓ 4 callers
Method
tool_arg_name
common/chat-peg-parser.h:88
↓ 4 callers
Method
tool_arg_open
common/chat-peg-parser.h:86
↓ 4 callers
Method
tool_arg_string_value
Use for schema-declared string types - won't be treated as potential JSON container
common/chat-peg-parser.h:92
↓ 4 callers
Function
transform_to_str
tools/llama-bench/llama-bench.cpp:94
↓ 4 callers
Function
transpose_2d_as_8b
ggml/src/ggml-opencl/ggml-opencl.cpp:3371
↓ 4 callers
Function
transpose_8x8_32bit
ggml/src/ggml-cpu/amx/mmq.cpp:265
↓ 4 callers
Method
traverse
src/llama-vocab.cpp:58
↓ 4 callers
Function
tty_can_use_colors
common/common.cpp:1041
↓ 4 callers
Function
unicode_cpt_from_utf8
src/unicode.cpp:30
↓ 4 callers
Function
unpack_32_4
ggml/src/ggml-openvino/ggml-quants.cpp:33
↓ 4 callers
Method
updateConversationTitleWithConfirmation
* Updates conversation title with optional confirmation dialog based on settings * @param convId - The conversation ID to update * @param newTitle
tools/server/webui/src/lib/stores/conversations.svelte.ts:463
↓ 4 callers
Function
validate_fp16
ggml/src/ggml-quants.c:5184
↓ 4 callers
Function
value_compare
compare operator for value_t
common/jinja/value.cpp:1289
↓ 4 callers
Function
vk_op_sum_rows_push_constants_init
ggml/src/ggml-vulkan/ggml-vulkan.cpp:1581
↓ 4 callers
Function
vmaxvq_f32
ggml/src/ggml-cpu/ggml-cpu-impl.h:126
↓ 4 callers
Function
weight1
ggml/src/ggml-sycl/upscale.cpp:186
↓ 4 callers
Function
weight2
ggml/src/ggml-sycl/upscale.cpp:187
↓ 4 callers
Function
wrap_add
ggml/src/ggml-sycl/roll.cpp:6
↓ 4 callers
Function
writeString
(offset: number, string: string)
tools/server/webui/src/lib/utils/audio-recording.ts:165
↓ 3 callers
Method
#buildMcpClientConfig
* Builds MCP client configuration from settings.
tools/server/webui/src/lib/stores/mcp.svelte.ts:226
↓ 3 callers
Function
SHA1Final
examples/gguf-hash/deps/sha1/sha1.c:231
↓ 3 callers
Function
SHA1Init
examples/gguf-hash/deps/sha1/sha1.c:182
↓ 3 callers
Function
XXH3_consumeStripes
! * @internal * @brief Processes a large input for XXH3_update() and XXH3_digest_long(). * * Unlike XXH3_hashLong_internal_loop(), this can proces
examples/gguf-hash/deps/xxhash/xxhash.h:6258
↓ 3 callers
Function
XXH3_mul128_fold64
! * @brief Calculates a 64-bit to 128-bit multiply, then XOR folds it. * * The reason for the separate function is to prevent passing too many stru
examples/gguf-hash/deps/xxhash/xxhash.h:4489
↓ 3 callers
Function
XXH_free
examples/gguf-hash/deps/xxhash/xxhash.h:2358
↓ 3 callers
Function
XXH_malloc
examples/gguf-hash/deps/xxhash/xxhash.h:2357
↓ 3 callers
Function
XXH_readBE64
examples/gguf-hash/deps/xxhash/xxhash.h:3341
↓ 3 callers
Function
XXH_vec_loadu
! * Performs an unaligned vector load and byte swaps it on big endian. */
examples/gguf-hash/deps/xxhash/xxhash.h:4203
↓ 3 callers
Function
____m256i
Convert __m128i to __m256i
ggml/src/ggml-cpu/arch/loongarch/quants.c:133
↓ 3 callers
Method
__init__
(self)
gguf-py/gguf/scripts/gguf_editor_gui.py:815
↓ 3 callers
Function
_build_repetition
(item_rule, min_items, max_items, separator_rule=None)
examples/json_schema_to_grammar.py:11
↓ 3 callers
Method
_check_keys
Private helper method that checks against required data keys and returns missing ones.
scripts/compare-llama-bench.py:241
↓ 3 callers
Method
_create_vocab_sentencepiece
(self)
convert_hf_to_gguf.py:1660
↓ 3 callers
Method
_doStartObserving
()
tools/server/webui/src/lib/hooks/use-auto-scroll.svelte.ts:210
↓ 3 callers
Method
_format_literal
(self, literal)
examples/json_schema_to_grammar.py:251
↓ 3 callers
Method
_generate_constant_rule
(self, value)
examples/json_schema_to_grammar.py:565
↓ 3 callers
Method
_get_str
(self, offset: int)
gguf-py/gguf/gguf_reader.py:217
↓ 3 callers
Method
_pack_val
(self, val: Any, vtype: GGUFValueType, add_vtype: bool, sub_type: GGUFValueType | None = None)
gguf-py/gguf/gguf_writer.py:1310
↓ 3 callers
Method
_recurse_apply
(o: Any, fn: Callable[[Any], Any])
gguf-py/gguf/lazy.py:100
↓ 3 callers
Method
_set_vocab_builtin
(self, model_name: Literal["gpt-neox", "llama-spm"], vocab_size: int)
convert_hf_to_gguf.py:1817
↓ 3 callers
Method
_set_vocab_glm
(self)
convert_hf_to_gguf.py:1911
↓ 3 callers
Method
_set_vocab_llama_hf
(self)
convert_hf_to_gguf.py:1750
↓ 3 callers
Method
_set_vocab_mistral
(self)
convert_hf_to_gguf.py:1977
↓ 3 callers
Method
_skip_layer_tensor
(self, stripped_name: str)
convert_hf_to_gguf.py:9294
↓ 3 callers
Function
_util_sparse_array_node_alloc
ggml/src/ggml-virtgpu/virtgpu-utils.cpp:94
↓ 3 callers
Function
_util_sparse_array_set_or_free_node
ggml/src/ggml-virtgpu/virtgpu-utils.cpp:108
↓ 3 callers
Function
aclnn_index_select_4d
* @brief Performs index select operation on a 4D tensor using the CANN backend. * * This function applies the `IndexSelect` operation along a specif
ggml/src/ggml-cann/aclnn_ops.cpp:1717
↓ 3 callers
Function
aclnn_pad
* @brief Pads a tensor with a specified value along each dimension. * * This function performs padding of the source tensor `acl_src` and stores the
ggml/src/ggml-cann/aclnn_ops.cpp:680
↓ 3 callers
Method
add_add_eos_token
(self, value: bool)
gguf-py/gguf/gguf_writer.py:1090
↓ 3 callers
Method
add_clamp_kqv
(self, value: float)
gguf-py/gguf/gguf_writer.py:796
↓ 3 callers
Method
add_clip_audio_projector_type
(self, value: str)
gguf-py/gguf/gguf_writer.py:1260
↓ 3 callers
Method
add_clip_vision_projector_type
(self, value: str)
gguf-py/gguf/gguf_writer.py:1154
↓ 3 callers
Method
add_embedding_scale
(self, value: float)
gguf-py/gguf/gguf_writer.py:886
↓ 3 callers
Method
add_final_logit_softcapping
(self, value: float)
gguf-py/gguf/gguf_writer.py:823
↓ 3 callers
Method
add_key_length_mla
(self, length: int)
gguf-py/gguf/gguf_writer.py:772
↓ 3 callers
Method
add_license
(self, license: str)
gguf-py/gguf/gguf_writer.py:577
↓ 3 callers
Method
add_mask_token_id
(self, id: int)
gguf-py/gguf/gguf_writer.py:1084
↓ 3 callers
Method
add_max_alibi_bias
(self, bias: float)
gguf-py/gguf/gguf_writer.py:793
↓ 3 callers
Method
add_pooling_type
(self, value: PoolingType)
gguf-py/gguf/gguf_writer.py:976
↓ 3 callers
Method
add_precompiled_charsmap
(self, charsmap: bytes)
gguf-py/gguf/gguf_writer.py:1102
↓ 3 callers
Method
add_remove_extra_whitespaces
(self, value: bool)
gguf-py/gguf/gguf_writer.py:1099
↓ 3 callers
Method
add_rope_scaling_yarn_beta_fast
(self, value: float)
gguf-py/gguf/gguf_writer.py:1021
↓ 3 callers
Method
add_rope_scaling_yarn_beta_slow
(self, value: float)
gguf-py/gguf/gguf_writer.py:1024
↓ 3 callers
Method
add_value_length_mla
(self, length: int)
gguf-py/gguf/gguf_writer.py:775
↓ 3 callers
Method
alloc_buffer
ggml/src/ggml-rpc/ggml-rpc.cpp:928
↓ 3 callers
Function
apiFetch
(path: string, options: ApiFetchOptions = {})
tools/server/webui/src/lib/utils/api-fetch.ts:46
↓ 3 callers
Function
apir_decode_char_array
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:316
↓ 3 callers
Function
apir_decode_uint64_t
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:168
↓ 3 callers
Function
apir_decoder_alloc_array
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:328
↓ 3 callers
Function
apir_encode_char_array
ggml/src/ggml-virtgpu/backend/shared/apir_cs.h:311
↓ 3 callers
Function
apir_initialize
ggml/src/ggml-virtgpu/ggml-backend-reg.cpp:9
↓ 3 callers
Function
are_lora_equal
tools/server/server-common.cpp:143
↓ 3 callers
Method
autoReconnect
* Auto-reconnect to a server with exponential backoff. * Continues indefinitely until successful. * * Race-condition safety: when the phase call
tools/server/webui/src/lib/stores/mcp.svelte.ts:842
← previous
next →
1,901–2,000 of 13,473, ranked by callers